Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 291 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.7722. Min Act: -0.1700
Data Index: 5673772 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.7097. Min Act: -0.1700
Data Index: 2113480 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.5222. Min Act: -0.1700
Data Index: 8333889 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.4909. Min Act: -0.1700
Data Index: 3155565 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.4597. Min Act: -0.1700
Data Index: 2006670 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.4597. Min Act: -0.1700
Data Index: 6160797 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.4284. Min Act: -0.1700
Data Index: 4716965 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.3972. Min Act: -0.1700
Data Index: 1748963 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.3972. Min Act: -0.1700
Data Index: 8200416 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.3659. Min Act: -0.1700
Data Index: 1503885 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.3659. Min Act: -0.1700
Data Index: 3980623 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.3347. Min Act: -0.1700
Data Index: 4534724 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.3659. Min Act: -0.1700
Data Index: 2873341 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.3347. Min Act: -0.1700
Data Index: 6316337 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.3347. Min Act: -0.1700
Data Index: 5910717 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.3034. Min Act: -0.1700
Data Index: 6725118 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.2722. Min Act: -0.1700
Data Index: 396780 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.3034. Min Act: -0.1700
Data Index: 5891141 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.2409. Min Act: -0.1700
Data Index: 5341730 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7722. Min Range: -6.7722
Max Act: 6.2409. Min Act: -0.1700
Data Index: 2836793 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19