Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3898 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2393. Min Range: -6.2393
Max Act: 6.2393. Min Act: -0.1700
Data Index: 3510167 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2393. Min Range: -6.2393
Max Act: 6.0831. Min Act: -0.1700
Data Index: 8510558 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2393. Min Range: -6.2393
Max Act: 5.9581. Min Act: -0.1700
Data Index: 739190 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2393. Min Range: -6.2393
Max Act: 5.9581. Min Act: -0.1700
Data Index: 1014895 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2393. Min Range: -6.2393
Max Act: 5.9268. Min Act: -0.1700
Data Index: 4386840 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2393. Min Range: -6.2393
Max Act: 5.8956. Min Act: -0.1700
Data Index: 6902795 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2393. Min Range: -6.2393
Max Act: 5.8956. Min Act: -0.1700
Data Index: 2921998 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2393. Min Range: -6.2393
Max Act: 5.8643. Min Act: -0.1700
Data Index: 3766450 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2393. Min Range: -6.2393
Max Act: 5.8956. Min Act: -0.1700
Data Index: 7955662 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2393. Min Range: -6.2393
Max Act: 5.8331. Min Act: -0.1700
Data Index: 2003615 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2393. Min Range: -6.2393
Max Act: 5.8018. Min Act: -0.1700
Data Index: 2889272 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2393. Min Range: -6.2393
Max Act: 5.7706. Min Act: -0.1700
Data Index: 6471117 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2393. Min Range: -6.2393
Max Act: 5.7706. Min Act: -0.1700
Data Index: 2267411 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2393. Min Range: -6.2393
Max Act: 5.7706. Min Act: -0.1700
Data Index: 4228443 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2393. Min Range: -6.2393
Max Act: 5.7393. Min Act: -0.1700
Data Index: 2628342 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2393. Min Range: -6.2393
Max Act: 5.7393. Min Act: -0.1700
Data Index: 7980021 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2393. Min Range: -6.2393
Max Act: 5.7393. Min Act: -0.1700
Data Index: 8390974 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2393. Min Range: -6.2393
Max Act: 5.7081. Min Act: -0.1700
Data Index: 7575407 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2393. Min Range: -6.2393
Max Act: 5.7081. Min Act: -0.1700
Data Index: 552616 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2393. Min Range: -6.2393
Max Act: 5.7393. Min Act: -0.1700
Data Index: 8703090 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19