Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 952 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.6072. Min Act: -0.1700
Data Index: 1879418 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.5916. Min Act: -0.1700
Data Index: 7822747 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.5916. Min Act: -0.1700
Data Index: 5316914 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.5603. Min Act: -0.1700
Data Index: 7327594 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.4976. Min Act: -0.1700
Data Index: 8662742 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.4663. Min Act: -0.1700
Data Index: 7020912 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.4506. Min Act: -0.1700
Data Index: 3049938 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.4663. Min Act: -0.1700
Data Index: 3079813 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.4193. Min Act: -0.1700
Data Index: 8662743 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.4506. Min Act: -0.1700
Data Index: 4549198 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.4193. Min Act: -0.1700
Data Index: 1779193 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3723. Min Act: -0.1700
Data Index: 781373 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3566. Min Act: -0.1700
Data Index: 2484082 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3095. Min Act: -0.1700
Data Index: 7258979 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3409. Min Act: -0.1700
Data Index: 3396357 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3252. Min Act: -0.1700
Data Index: 7616464 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3252. Min Act: -0.1700
Data Index: 3467722 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.2938. Min Act: -0.1700
Data Index: 2243528 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.3095. Min Act: -0.1700
Data Index: 5947259 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6072. Min Range: -3.6072
Max Act: 3.2781. Min Act: -0.1700
Data Index: 3871397 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19