Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2736 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.3805. Min Act: -0.1700
Data Index: 6758556 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.3493. Min Act: -0.1700
Data Index: 7558787 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.2868. Min Act: -0.1700
Data Index: 1415340 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.2868. Min Act: -0.1700
Data Index: 5501280 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.2555. Min Act: -0.1700
Data Index: 4800833 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.2555. Min Act: -0.1700
Data Index: 2746422 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.2243. Min Act: -0.1700
Data Index: 5074184 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.2243. Min Act: -0.1700
Data Index: 1506541 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.2243. Min Act: -0.1700
Data Index: 2946037 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.1618. Min Act: -0.1700
Data Index: 4591327 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.1618. Min Act: -0.1700
Data Index: 7944091 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.1618. Min Act: -0.1700
Data Index: 7959344 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.1305. Min Act: -0.1700
Data Index: 577042 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.1305. Min Act: -0.1700
Data Index: 290420 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.0993. Min Act: -0.1700
Data Index: 625059 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.1305. Min Act: -0.1700
Data Index: 6076505 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.1305. Min Act: -0.1700
Data Index: 4721464 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.0993. Min Act: -0.1700
Data Index: 7787190 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.0993. Min Act: -0.1700
Data Index: 4283422 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3805. Min Range: -5.3805
Max Act: 5.0993. Min Act: -0.1700
Data Index: 1014067 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19