Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1550 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1687. Min Range: -6.1687
Max Act: 6.1687. Min Act: -0.1700
Data Index: 6008694 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1687. Min Range: -6.1687
Max Act: 5.7937. Min Act: -0.1700
Data Index: 8084899 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1687. Min Range: -6.1687
Max Act: 5.7625. Min Act: -0.1700
Data Index: 3472650 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1687. Min Range: -6.1687
Max Act: 5.7312. Min Act: -0.1700
Data Index: 5030475 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1687. Min Range: -6.1687
Max Act: 5.6687. Min Act: -0.1700
Data Index: 6008693 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1687. Min Range: -6.1687
Max Act: 5.6375. Min Act: -0.1700
Data Index: 3472631 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1687. Min Range: -6.1687
Max Act: 5.6687. Min Act: -0.1700
Data Index: 723874 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1687. Min Range: -6.1687
Max Act: 5.6062. Min Act: -0.1700
Data Index: 6008698 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1687. Min Range: -6.1687
Max Act: 5.6375. Min Act: -0.1700
Data Index: 5095441 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1687. Min Range: -6.1687
Max Act: 5.6062. Min Act: -0.1700
Data Index: 8765318 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1687. Min Range: -6.1687
Max Act: 5.6375. Min Act: -0.1700
Data Index: 3061735 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1687. Min Range: -6.1687
Max Act: 5.6375. Min Act: -0.1700
Data Index: 5942777 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1687. Min Range: -6.1687
Max Act: 5.6062. Min Act: -0.1700
Data Index: 3619148 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1687. Min Range: -6.1687
Max Act: 5.5750. Min Act: -0.1700
Data Index: 4139985 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1687. Min Range: -6.1687
Max Act: 5.5750. Min Act: -0.1700
Data Index: 1227161 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1687. Min Range: -6.1687
Max Act: 5.5125. Min Act: -0.1700
Data Index: 5095440 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1687. Min Range: -6.1687
Max Act: 5.5750. Min Act: -0.1700
Data Index: 6615171 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1687. Min Range: -6.1687
Max Act: 5.5437. Min Act: -0.1700
Data Index: 4042244 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1687. Min Range: -6.1687
Max Act: 5.5437. Min Act: -0.1700
Data Index: 4215035 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1687. Min Range: -6.1687
Max Act: 5.5125. Min Act: -0.1700
Data Index: 6843845 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19