Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6136 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.9177. Min Act: -0.1700
Data Index: 4989050 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.6052. Min Act: -0.1700
Data Index: 6102251 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.5427. Min Act: -0.1700
Data Index: 254318 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.4802. Min Act: -0.1700
Data Index: 4453486 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.4802. Min Act: -0.1700
Data Index: 3140419 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.4177. Min Act: -0.1700
Data Index: 4474471 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.4177. Min Act: -0.1700
Data Index: 8454838 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.4177. Min Act: -0.1700
Data Index: 7777969 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.3552. Min Act: -0.1700
Data Index: 7392121 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.4177. Min Act: -0.1700
Data Index: 5688403 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.3552. Min Act: -0.1700
Data Index: 1494253 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.2927. Min Act: -0.1700
Data Index: 6783713 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.2927. Min Act: -0.1700
Data Index: 1798003 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.2927. Min Act: -0.1700
Data Index: 5041995 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.2927. Min Act: -0.1700
Data Index: 333746 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.2302. Min Act: -0.1700
Data Index: 5027830 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.2302. Min Act: -0.1700
Data Index: 3930805 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.2302. Min Act: -0.1700
Data Index: 1372811 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.2302. Min Act: -0.1700
Data Index: 4517727 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9177. Min Range: -10.9177
Max Act: 10.2302. Min Act: -0.1700
Data Index: 2795241 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19