Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3442 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.6355. Min Act: -0.1700
Data Index: 8432337 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.6043. Min Act: -0.1700
Data Index: 5370020 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.4793. Min Act: -0.1700
Data Index: 2792383 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.5105. Min Act: -0.1700
Data Index: 6052785 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.4480. Min Act: -0.1700
Data Index: 4673394 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.4168. Min Act: -0.1700
Data Index: 4819904 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.4480. Min Act: -0.1700
Data Index: 8113444 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.3855. Min Act: -0.1700
Data Index: 2784732 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.3855. Min Act: -0.1700
Data Index: 3023667 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.4168. Min Act: -0.1700
Data Index: 5170992 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.3543. Min Act: -0.1700
Data Index: 7602281 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.3543. Min Act: -0.1700
Data Index: 582640 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.3543. Min Act: -0.1700
Data Index: 3376969 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.3543. Min Act: -0.1700
Data Index: 4172345 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.3543. Min Act: -0.1700
Data Index: 4131384 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.2918. Min Act: -0.1700
Data Index: 360871 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.3230. Min Act: -0.1700
Data Index: 6738716 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.3230. Min Act: -0.1700
Data Index: 6507357 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.3230. Min Act: -0.1700
Data Index: 72582 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6355. Min Range: -5.6355
Max Act: 5.3230. Min Act: -0.1700
Data Index: 6962006 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19