Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2935 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2866. Min Range: -6.2866
Max Act: 6.2866. Min Act: -0.1700
Data Index: 7526184 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2866. Min Range: -6.2866
Max Act: 6.1929. Min Act: -0.1700
Data Index: 90673 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2866. Min Range: -6.2866
Max Act: 6.1304. Min Act: -0.1700
Data Index: 4473451 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2866. Min Range: -6.2866
Max Act: 6.0991. Min Act: -0.1700
Data Index: 4438056 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2866. Min Range: -6.2866
Max Act: 5.9741. Min Act: -0.1700
Data Index: 7496258 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2866. Min Range: -6.2866
Max Act: 5.9429. Min Act: -0.1700
Data Index: 6243333 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2866. Min Range: -6.2866
Max Act: 5.8179. Min Act: -0.1700
Data Index: 1754272 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2866. Min Range: -6.2866
Max Act: 5.8179. Min Act: -0.1700
Data Index: 8180477 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2866. Min Range: -6.2866
Max Act: 5.8179. Min Act: -0.1700
Data Index: 3061079 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2866. Min Range: -6.2866
Max Act: 5.7866. Min Act: -0.1700
Data Index: 2602502 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2866. Min Range: -6.2866
Max Act: 5.7866. Min Act: -0.1700
Data Index: 5189539 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2866. Min Range: -6.2866
Max Act: 5.7554. Min Act: -0.1700
Data Index: 706332 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2866. Min Range: -6.2866
Max Act: 5.7554. Min Act: -0.1700
Data Index: 6322219 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2866. Min Range: -6.2866
Max Act: 5.7554. Min Act: -0.1700
Data Index: 7293238 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2866. Min Range: -6.2866
Max Act: 5.7554. Min Act: -0.1700
Data Index: 1933931 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2866. Min Range: -6.2866
Max Act: 5.7241. Min Act: -0.1700
Data Index: 4855241 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2866. Min Range: -6.2866
Max Act: 5.7241. Min Act: -0.1700
Data Index: 3462574 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2866. Min Range: -6.2866
Max Act: 5.6929. Min Act: -0.1700
Data Index: 8727535 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2866. Min Range: -6.2866
Max Act: 5.6929. Min Act: -0.1700
Data Index: 6065572 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2866. Min Range: -6.2866
Max Act: 5.6929. Min Act: -0.1700
Data Index: 8086053 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19