Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3787 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7210. Min Range: -7.7210
Max Act: 7.7210. Min Act: -0.1700
Data Index: 2587090 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7210. Min Range: -7.7210
Max Act: 7.5648. Min Act: -0.1700
Data Index: 1779637 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7210. Min Range: -7.7210
Max Act: 7.5960. Min Act: -0.1700
Data Index: 1353199 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7210. Min Range: -7.7210
Max Act: 7.4398. Min Act: -0.1700
Data Index: 6750517 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7210. Min Range: -7.7210
Max Act: 7.3460. Min Act: -0.1700
Data Index: 8621500 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7210. Min Range: -7.7210
Max Act: 7.2523. Min Act: -0.1700
Data Index: 6003648 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7210. Min Range: -7.7210
Max Act: 7.2210. Min Act: -0.1700
Data Index: 540426 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7210. Min Range: -7.7210
Max Act: 7.2210. Min Act: -0.1700
Data Index: 437162 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7210. Min Range: -7.7210
Max Act: 7.2210. Min Act: -0.1700
Data Index: 3330500 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7210. Min Range: -7.7210
Max Act: 7.1273. Min Act: -0.1700
Data Index: 559575 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7210. Min Range: -7.7210
Max Act: 7.0960. Min Act: -0.1700
Data Index: 1946342 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7210. Min Range: -7.7210
Max Act: 7.0648. Min Act: -0.1700
Data Index: 7546677 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7210. Min Range: -7.7210
Max Act: 7.0648. Min Act: -0.1700
Data Index: 7269194 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7210. Min Range: -7.7210
Max Act: 7.0023. Min Act: -0.1700
Data Index: 6300404 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7210. Min Range: -7.7210
Max Act: 7.0023. Min Act: -0.1700
Data Index: 3425396 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7210. Min Range: -7.7210
Max Act: 7.0023. Min Act: -0.1700
Data Index: 8726282 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7210. Min Range: -7.7210
Max Act: 7.0023. Min Act: -0.1700
Data Index: 2067365 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7210. Min Range: -7.7210
Max Act: 7.0023. Min Act: -0.1700
Data Index: 3270773 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7210. Min Range: -7.7210
Max Act: 7.0023. Min Act: -0.1700
Data Index: 5313462 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7210. Min Range: -7.7210
Max Act: 6.9710. Min Act: -0.1700
Data Index: 6750515 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19