Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3073 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3916. Min Range: -7.3916
Max Act: 7.3916. Min Act: -0.1700
Data Index: 2920172 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3916. Min Range: -7.3916
Max Act: 7.1103. Min Act: -0.1700
Data Index: 2353276 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3916. Min Range: -7.3916
Max Act: 7.0791. Min Act: -0.1700
Data Index: 3841090 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3916. Min Range: -7.3916
Max Act: 7.0791. Min Act: -0.1700
Data Index: 1965659 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3916. Min Range: -7.3916
Max Act: 7.0478. Min Act: -0.1700
Data Index: 5258866 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3916. Min Range: -7.3916
Max Act: 7.0791. Min Act: -0.1700
Data Index: 3065269 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3916. Min Range: -7.3916
Max Act: 7.0166. Min Act: -0.1700
Data Index: 5751155 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3916. Min Range: -7.3916
Max Act: 7.0166. Min Act: -0.1700
Data Index: 5031045 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3916. Min Range: -7.3916
Max Act: 6.9853. Min Act: -0.1700
Data Index: 1767486 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3916. Min Range: -7.3916
Max Act: 6.9853. Min Act: -0.1700
Data Index: 3270732 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3916. Min Range: -7.3916
Max Act: 7.0166. Min Act: -0.1700
Data Index: 2351978 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3916. Min Range: -7.3916
Max Act: 6.9541. Min Act: -0.1700
Data Index: 7351884 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3916. Min Range: -7.3916
Max Act: 6.9228. Min Act: -0.1700
Data Index: 8742746 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3916. Min Range: -7.3916
Max Act: 6.9228. Min Act: -0.1700
Data Index: 1249027 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3916. Min Range: -7.3916
Max Act: 6.9228. Min Act: -0.1700
Data Index: 790800 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3916. Min Range: -7.3916
Max Act: 6.8916. Min Act: -0.1700
Data Index: 614975 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3916. Min Range: -7.3916
Max Act: 6.8916. Min Act: -0.1700
Data Index: 5661941 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3916. Min Range: -7.3916
Max Act: 6.8916. Min Act: -0.1700
Data Index: 589658 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3916. Min Range: -7.3916
Max Act: 6.8603. Min Act: -0.1700
Data Index: 3821883 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3916. Min Range: -7.3916
Max Act: 6.8603. Min Act: -0.1700
Data Index: 2017730 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19