Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3264 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.9912. Min Act: -0.1700
Data Index: 6648427 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.9595. Min Act: -0.1700
Data Index: 2395642 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.9595. Min Act: -0.1700
Data Index: 6933175 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.9120. Min Act: -0.1700
Data Index: 7907466 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.8962. Min Act: -0.1700
Data Index: 616889 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.8962. Min Act: -0.1700
Data Index: 6544505 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.9120. Min Act: -0.1700
Data Index: 8190384 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.8644. Min Act: -0.1700
Data Index: 8700648 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.8485. Min Act: -0.1700
Data Index: 6376388 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.8326. Min Act: -0.1700
Data Index: 8308782 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.8167. Min Act: -0.1700
Data Index: 55190 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.8167. Min Act: -0.1700
Data Index: 265320 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.8167. Min Act: -0.1700
Data Index: 3993817 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.8167. Min Act: -0.1700
Data Index: 7853259 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.8167. Min Act: -0.1700
Data Index: 7993834 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.8167. Min Act: -0.1700
Data Index: 4671422 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.8008. Min Act: -0.1700
Data Index: 278246 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.7849. Min Act: -0.1700
Data Index: 5607871 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.7849. Min Act: -0.1700
Data Index: 205185 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9912. Min Range: -2.9912
Max Act: 2.7690. Min Act: -0.1700
Data Index: 555658 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19