Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3074 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.5540. Min Range: -11.5540
Max Act: 11.5540. Min Act: -0.1700
Data Index: 4855524 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5540. Min Range: -11.5540
Max Act: 11.1790. Min Act: -0.1700
Data Index: 2630235 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5540. Min Range: -11.5540
Max Act: 10.8665. Min Act: -0.1700
Data Index: 511850 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5540. Min Range: -11.5540
Max Act: 10.6790. Min Act: -0.1700
Data Index: 5511993 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5540. Min Range: -11.5540
Max Act: 10.4915. Min Act: -0.1700
Data Index: 145855 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5540. Min Range: -11.5540
Max Act: 10.4915. Min Act: -0.1700
Data Index: 254268 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5540. Min Range: -11.5540
Max Act: 10.4290. Min Act: -0.1700
Data Index: 4421043 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5540. Min Range: -11.5540
Max Act: 10.4290. Min Act: -0.1700
Data Index: 2229196 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5540. Min Range: -11.5540
Max Act: 10.3665. Min Act: -0.1700
Data Index: 5431363 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5540. Min Range: -11.5540
Max Act: 10.3665. Min Act: -0.1700
Data Index: 2796953 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5540. Min Range: -11.5540
Max Act: 10.3665. Min Act: -0.1700
Data Index: 1495237 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5540. Min Range: -11.5540
Max Act: 10.4290. Min Act: -0.1700
Data Index: 4051455 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5540. Min Range: -11.5540
Max Act: 10.3665. Min Act: -0.1700
Data Index: 4202913 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5540. Min Range: -11.5540
Max Act: 10.2415. Min Act: -0.1700
Data Index: 8119738 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5540. Min Range: -11.5540
Max Act: 10.3040. Min Act: -0.1700
Data Index: 1199821 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5540. Min Range: -11.5540
Max Act: 10.2415. Min Act: -0.1700
Data Index: 3586642 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5540. Min Range: -11.5540
Max Act: 10.1790. Min Act: -0.1700
Data Index: 905846 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5540. Min Range: -11.5540
Max Act: 10.2415. Min Act: -0.1700
Data Index: 3277087 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5540. Min Range: -11.5540
Max Act: 10.1790. Min Act: -0.1700
Data Index: 8015657 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5540. Min Range: -11.5540
Max Act: 10.1790. Min Act: -0.1700
Data Index: 2995193 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19