Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2919 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.9866. Min Act: -0.1700
Data Index: 5129280 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.7834. Min Act: -0.1700
Data Index: 631682 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.7521. Min Act: -0.1700
Data Index: 539980 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.7208. Min Act: -0.1700
Data Index: 5337902 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.7208. Min Act: -0.1700
Data Index: 4038939 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.6739. Min Act: -0.1700
Data Index: 8755301 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.6739. Min Act: -0.1700
Data Index: 2778851 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.6583. Min Act: -0.1700
Data Index: 1564442 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.6426. Min Act: -0.1700
Data Index: 1437656 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.6113. Min Act: -0.1700
Data Index: 6632382 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.6113. Min Act: -0.1700
Data Index: 5993693 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.5800. Min Act: -0.1700
Data Index: 7829235 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.5800. Min Act: -0.1700
Data Index: 8183667 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.5957. Min Act: -0.1700
Data Index: 4589505 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.5800. Min Act: -0.1700
Data Index: 889386 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.5644. Min Act: -0.1700
Data Index: 5081916 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.5487. Min Act: -0.1700
Data Index: 652451 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.5487. Min Act: -0.1700
Data Index: 3217519 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.5174. Min Act: -0.1700
Data Index: 7809886 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9866. Min Range: -3.9866
Max Act: 3.5174. Min Act: -0.1700
Data Index: 6854711 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19