Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4612 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3042. Min Range: -5.3042
Max Act: 5.3042. Min Act: -0.1700
Data Index: 4095788 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3042. Min Range: -5.3042
Max Act: 5.0854. Min Act: -0.1700
Data Index: 2812810 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3042. Min Range: -5.3042
Max Act: 4.9917. Min Act: -0.1700
Data Index: 2501496 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3042. Min Range: -5.3042
Max Act: 4.9292. Min Act: -0.1700
Data Index: 5780377 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3042. Min Range: -5.3042
Max Act: 4.8979. Min Act: -0.1700
Data Index: 2792250 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3042. Min Range: -5.3042
Max Act: 4.8667. Min Act: -0.1700
Data Index: 3729288 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3042. Min Range: -5.3042
Max Act: 4.8354. Min Act: -0.1700
Data Index: 924193 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3042. Min Range: -5.3042
Max Act: 4.8042. Min Act: -0.1700
Data Index: 3265308 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3042. Min Range: -5.3042
Max Act: 4.8042. Min Act: -0.1700
Data Index: 6437202 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3042. Min Range: -5.3042
Max Act: 4.7729. Min Act: -0.1700
Data Index: 2159066 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3042. Min Range: -5.3042
Max Act: 4.7417. Min Act: -0.1700
Data Index: 8362343 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3042. Min Range: -5.3042
Max Act: 4.7417. Min Act: -0.1700
Data Index: 8160757 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3042. Min Range: -5.3042
Max Act: 4.7104. Min Act: -0.1700
Data Index: 2629014 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3042. Min Range: -5.3042
Max Act: 4.6792. Min Act: -0.1700
Data Index: 5819307 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3042. Min Range: -5.3042
Max Act: 4.7104. Min Act: -0.1700
Data Index: 1535807 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3042. Min Range: -5.3042
Max Act: 4.7104. Min Act: -0.1700
Data Index: 8807442 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3042. Min Range: -5.3042
Max Act: 4.6792. Min Act: -0.1700
Data Index: 287332 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3042. Min Range: -5.3042
Max Act: 4.6792. Min Act: -0.1700
Data Index: 6886612 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3042. Min Range: -5.3042
Max Act: 4.6792. Min Act: -0.1700
Data Index: 7511073 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3042. Min Range: -5.3042
Max Act: 4.7104. Min Act: -0.1700
Data Index: 4514353 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19