Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3176 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.5192. Min Act: -0.1700
Data Index: 6324389 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.4567. Min Act: -0.1700
Data Index: 8780285 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.2692. Min Act: -0.1700
Data Index: 4617239 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.3317. Min Act: -0.1700
Data Index: 29569 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.3005. Min Act: -0.1700
Data Index: 1182694 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.2692. Min Act: -0.1700
Data Index: 6919520 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.2380. Min Act: -0.1700
Data Index: 8333852 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.2067. Min Act: -0.1700
Data Index: 6655817 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.2067. Min Act: -0.1700
Data Index: 1011947 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.2067. Min Act: -0.1700
Data Index: 7054159 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.2067. Min Act: -0.1700
Data Index: 6630459 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.1755. Min Act: -0.1700
Data Index: 7202638 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.1442. Min Act: -0.1700
Data Index: 1132435 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.1130. Min Act: -0.1700
Data Index: 8442634 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.1442. Min Act: -0.1700
Data Index: 8336156 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.1442. Min Act: -0.1700
Data Index: 7143933 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.1442. Min Act: -0.1700
Data Index: 6238524 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.1130. Min Act: -0.1700
Data Index: 890185 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.1130. Min Act: -0.1700
Data Index: 6810700 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5192. Min Range: -6.5192
Max Act: 6.1130. Min Act: -0.1700
Data Index: 198415 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19