Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2751 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.6414. Min Act: -0.1700
Data Index: 4801911 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.3289. Min Act: -0.1700
Data Index: 8407809 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.3289. Min Act: -0.1700
Data Index: 5337212 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.3289. Min Act: -0.1700
Data Index: 6335041 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.2976. Min Act: -0.1700
Data Index: 295642 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.2351. Min Act: -0.1700
Data Index: 162088 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.2351. Min Act: -0.1700
Data Index: 6338911 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.2351. Min Act: -0.1700
Data Index: 5887322 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.2664. Min Act: -0.1700
Data Index: 2887588 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.2351. Min Act: -0.1700
Data Index: 5140038 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.1726. Min Act: -0.1700
Data Index: 1955708 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.1726. Min Act: -0.1700
Data Index: 1412629 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.1414. Min Act: -0.1700
Data Index: 5929302 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.1726. Min Act: -0.1700
Data Index: 7151802 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.1726. Min Act: -0.1700
Data Index: 2879425 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.1726. Min Act: -0.1700
Data Index: 7075630 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.1101. Min Act: -0.1700
Data Index: 6543001 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.1414. Min Act: -0.1700
Data Index: 7588568 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.1414. Min Act: -0.1700
Data Index: 748521 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6414. Min Range: -6.6414
Max Act: 6.1101. Min Act: -0.1700
Data Index: 544218 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19