Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3489 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1885. Min Range: -6.1885
Max Act: 6.1885. Min Act: -0.1700
Data Index: 3139128 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1885. Min Range: -6.1885
Max Act: 6.0010. Min Act: -0.1700
Data Index: 1993205 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1885. Min Range: -6.1885
Max Act: 5.9072. Min Act: -0.1700
Data Index: 6820217 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1885. Min Range: -6.1885
Max Act: 5.8447. Min Act: -0.1700
Data Index: 2037755 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1885. Min Range: -6.1885
Max Act: 5.8447. Min Act: -0.1700
Data Index: 1773996 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1885. Min Range: -6.1885
Max Act: 5.8135. Min Act: -0.1700
Data Index: 4030591 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1885. Min Range: -6.1885
Max Act: 5.7510. Min Act: -0.1700
Data Index: 4057426 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1885. Min Range: -6.1885
Max Act: 5.7197. Min Act: -0.1700
Data Index: 7654832 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1885. Min Range: -6.1885
Max Act: 5.6885. Min Act: -0.1700
Data Index: 1084275 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1885. Min Range: -6.1885
Max Act: 5.6885. Min Act: -0.1700
Data Index: 1141127 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1885. Min Range: -6.1885
Max Act: 5.6572. Min Act: -0.1700
Data Index: 4824379 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1885. Min Range: -6.1885
Max Act: 5.6260. Min Act: -0.1700
Data Index: 6416199 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1885. Min Range: -6.1885
Max Act: 5.6260. Min Act: -0.1700
Data Index: 4014523 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1885. Min Range: -6.1885
Max Act: 5.5947. Min Act: -0.1700
Data Index: 7043547 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1885. Min Range: -6.1885
Max Act: 5.5947. Min Act: -0.1700
Data Index: 1436378 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1885. Min Range: -6.1885
Max Act: 5.5947. Min Act: -0.1700
Data Index: 2534431 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1885. Min Range: -6.1885
Max Act: 5.5947. Min Act: -0.1700
Data Index: 3341624 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1885. Min Range: -6.1885
Max Act: 5.5947. Min Act: -0.1700
Data Index: 4030590 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1885. Min Range: -6.1885
Max Act: 5.5947. Min Act: -0.1700
Data Index: 1706217 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1885. Min Range: -6.1885
Max Act: 5.5947. Min Act: -0.1700
Data Index: 5306230 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19