Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6044 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4302. Min Range: -6.4302
Max Act: 6.4302. Min Act: -0.1700
Data Index: 6856783 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4302. Min Range: -6.4302
Max Act: 6.2740. Min Act: -0.1700
Data Index: 8154025 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4302. Min Range: -6.4302
Max Act: 6.2427. Min Act: -0.1700
Data Index: 6508673 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4302. Min Range: -6.4302
Max Act: 6.1802. Min Act: -0.1700
Data Index: 1216114 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4302. Min Range: -6.4302
Max Act: 6.1177. Min Act: -0.1700
Data Index: 6466138 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4302. Min Range: -6.4302
Max Act: 6.0865. Min Act: -0.1700
Data Index: 5070953 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4302. Min Range: -6.4302
Max Act: 6.0865. Min Act: -0.1700
Data Index: 4650378 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4302. Min Range: -6.4302
Max Act: 6.0865. Min Act: -0.1700
Data Index: 3796539 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4302. Min Range: -6.4302
Max Act: 6.0865. Min Act: -0.1700
Data Index: 1696619 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4302. Min Range: -6.4302
Max Act: 6.0552. Min Act: -0.1700
Data Index: 1830056 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4302. Min Range: -6.4302
Max Act: 6.0552. Min Act: -0.1700
Data Index: 7743038 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4302. Min Range: -6.4302
Max Act: 5.9927. Min Act: -0.1700
Data Index: 8047364 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4302. Min Range: -6.4302
Max Act: 6.0240. Min Act: -0.1700
Data Index: 6917257 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4302. Min Range: -6.4302
Max Act: 5.9927. Min Act: -0.1700
Data Index: 1141458 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4302. Min Range: -6.4302
Max Act: 5.9927. Min Act: -0.1700
Data Index: 946380 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4302. Min Range: -6.4302
Max Act: 5.9615. Min Act: -0.1700
Data Index: 1216119 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4302. Min Range: -6.4302
Max Act: 5.9615. Min Act: -0.1700
Data Index: 1047959 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4302. Min Range: -6.4302
Max Act: 5.9615. Min Act: -0.1700
Data Index: 7573466 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4302. Min Range: -6.4302
Max Act: 5.9302. Min Act: -0.1700
Data Index: 1969055 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4302. Min Range: -6.4302
Max Act: 5.9615. Min Act: -0.1700
Data Index: 7859400 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19