Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3323 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3805. Min Range: -6.3805
Max Act: 6.3805. Min Act: -0.1700
Data Index: 7163374 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3805. Min Range: -6.3805
Max Act: 6.3180. Min Act: -0.1700
Data Index: 7181543 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3805. Min Range: -6.3805
Max Act: 6.2555. Min Act: -0.1700
Data Index: 3734371 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3805. Min Range: -6.3805
Max Act: 6.1305. Min Act: -0.1700
Data Index: 7088785 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3805. Min Range: -6.3805
Max Act: 6.1305. Min Act: -0.1700
Data Index: 1876695 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3805. Min Range: -6.3805
Max Act: 5.9743. Min Act: -0.1700
Data Index: 3351774 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3805. Min Range: -6.3805
Max Act: 5.9118. Min Act: -0.1700
Data Index: 7308803 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3805. Min Range: -6.3805
Max Act: 5.8493. Min Act: -0.1700
Data Index: 4779037 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3805. Min Range: -6.3805
Max Act: 5.8493. Min Act: -0.1700
Data Index: 8601524 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3805. Min Range: -6.3805
Max Act: 5.8805. Min Act: -0.1700
Data Index: 4991323 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3805. Min Range: -6.3805
Max Act: 5.8493. Min Act: -0.1700
Data Index: 8163182 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3805. Min Range: -6.3805
Max Act: 5.8493. Min Act: -0.1700
Data Index: 8516103 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3805. Min Range: -6.3805
Max Act: 5.8805. Min Act: -0.1700
Data Index: 3373255 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3805. Min Range: -6.3805
Max Act: 5.7868. Min Act: -0.1700
Data Index: 7270285 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3805. Min Range: -6.3805
Max Act: 5.7555. Min Act: -0.1700
Data Index: 987026 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3805. Min Range: -6.3805
Max Act: 5.7868. Min Act: -0.1700
Data Index: 7116797 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3805. Min Range: -6.3805
Max Act: 5.7868. Min Act: -0.1700
Data Index: 3825421 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3805. Min Range: -6.3805
Max Act: 5.7868. Min Act: -0.1700
Data Index: 3183912 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3805. Min Range: -6.3805
Max Act: 5.7243. Min Act: -0.1700
Data Index: 7889441 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3805. Min Range: -6.3805
Max Act: 5.7243. Min Act: -0.1700
Data Index: 2799529 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19