Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3195 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.9368. Min Act: -0.1700
Data Index: 4415520 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.9368. Min Act: -0.1700
Data Index: 8282588 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.8743. Min Act: -0.1700
Data Index: 6829554 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.9056. Min Act: -0.1700
Data Index: 606868 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.8430. Min Act: -0.1700
Data Index: 8259762 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.8430. Min Act: -0.1700
Data Index: 865081 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.7492. Min Act: -0.1700
Data Index: 2135892 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.7492. Min Act: -0.1700
Data Index: 2449371 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.7492. Min Act: -0.1700
Data Index: 2599264 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.7492. Min Act: -0.1700
Data Index: 5776771 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.7492. Min Act: -0.1700
Data Index: 8394872 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.7492. Min Act: -0.1700
Data Index: 5760491 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.7179. Min Act: -0.1700
Data Index: 2894420 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.7492. Min Act: -0.1700
Data Index: 5031265 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.7179. Min Act: -0.1700
Data Index: 6928908 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.7492. Min Act: -0.1700
Data Index: 6352057 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.7179. Min Act: -0.1700
Data Index: 1804053 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.7179. Min Act: -0.1700
Data Index: 4351244 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.7179. Min Act: -0.1700
Data Index: 7126724 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9368. Min Range: -3.9368
Max Act: 3.6866. Min Act: -0.1700
Data Index: 6041078 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19