Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0253. Min Range: -5.0253
Max Act: 5.0253. Min Act: -0.1700
Data Index: 7520460 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.9003. Min Act: -0.1700
Data Index: 7709603 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.8066. Min Act: -0.1700
Data Index: 5625430 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.8378. Min Act: -0.1700
Data Index: 837007 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.8066. Min Act: -0.1700
Data Index: 6170654 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.8066. Min Act: -0.1700
Data Index: 3876450 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.7128. Min Act: -0.1700
Data Index: 3238058 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.7128. Min Act: -0.1700
Data Index: 6797180 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.7441. Min Act: -0.1700
Data Index: 8430792 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.6816. Min Act: -0.1700
Data Index: 899742 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.6816. Min Act: -0.1700
Data Index: 2767213 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.6503. Min Act: -0.1700
Data Index: 661274 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.6503. Min Act: -0.1700
Data Index: 2713246 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.6191. Min Act: -0.1700
Data Index: 238757 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.6191. Min Act: -0.1700
Data Index: 927428 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.5878. Min Act: -0.1700
Data Index: 2684692 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.5878. Min Act: -0.1700
Data Index: 3256330 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.6191. Min Act: -0.1700
Data Index: 2684691 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.6191. Min Act: -0.1700
Data Index: 7650849 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0253. Min Range: -5.0253
Max Act: 4.6191. Min Act: -0.1700
Data Index: 7709605 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19