Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 376 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2868. Min Range: -9.2868
Max Act: 9.2868. Min Act: -0.1700
Data Index: 4525619 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2868. Min Range: -9.2868
Max Act: 9.2868. Min Act: -0.1700
Data Index: 1000302 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2868. Min Range: -9.2868
Max Act: 9.2243. Min Act: -0.1700
Data Index: 8452988 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2868. Min Range: -9.2868
Max Act: 9.0368. Min Act: -0.1700
Data Index: 8284255 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2868. Min Range: -9.2868
Max Act: 8.9743. Min Act: -0.1700
Data Index: 7909335 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2868. Min Range: -9.2868
Max Act: 8.9743. Min Act: -0.1700
Data Index: 298241 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2868. Min Range: -9.2868
Max Act: 8.9118. Min Act: -0.1700
Data Index: 1269995 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2868. Min Range: -9.2868
Max Act: 8.7868. Min Act: -0.1700
Data Index: 1460653 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2868. Min Range: -9.2868
Max Act: 8.7243. Min Act: -0.1700
Data Index: 8542465 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2868. Min Range: -9.2868
Max Act: 8.7868. Min Act: -0.1700
Data Index: 3721597 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2868. Min Range: -9.2868
Max Act: 8.7868. Min Act: -0.1700
Data Index: 4939731 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2868. Min Range: -9.2868
Max Act: 8.7868. Min Act: -0.1700
Data Index: 8243842 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2868. Min Range: -9.2868
Max Act: 8.7868. Min Act: -0.1700
Data Index: 3101040 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2868. Min Range: -9.2868
Max Act: 8.7243. Min Act: -0.1700
Data Index: 3601099 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2868. Min Range: -9.2868
Max Act: 8.7243. Min Act: -0.1700
Data Index: 6172000 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2868. Min Range: -9.2868
Max Act: 8.7243. Min Act: -0.1700
Data Index: 6913734 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2868. Min Range: -9.2868
Max Act: 8.7243. Min Act: -0.1700
Data Index: 1672804 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2868. Min Range: -9.2868
Max Act: 8.7243. Min Act: -0.1700
Data Index: 7286476 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2868. Min Range: -9.2868
Max Act: 8.7243. Min Act: -0.1700
Data Index: 7715393 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2868. Min Range: -9.2868
Max Act: 8.7243. Min Act: -0.1700
Data Index: 208250 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19