Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 677 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0692. Min Range: -10.0692
Max Act: 10.0692. Min Act: -0.1700
Data Index: 5422928 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0692. Min Range: -10.0692
Max Act: 9.8817. Min Act: -0.1700
Data Index: 5411095 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0692. Min Range: -10.0692
Max Act: 9.8192. Min Act: -0.1700
Data Index: 2043473 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0692. Min Range: -10.0692
Max Act: 9.7567. Min Act: -0.1700
Data Index: 7758797 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0692. Min Range: -10.0692
Max Act: 9.6942. Min Act: -0.1700
Data Index: 5035920 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0692. Min Range: -10.0692
Max Act: 9.5692. Min Act: -0.1700
Data Index: 192512 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0692. Min Range: -10.0692
Max Act: 9.6317. Min Act: -0.1700
Data Index: 2221611 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0692. Min Range: -10.0692
Max Act: 9.5692. Min Act: -0.1700
Data Index: 3943199 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0692. Min Range: -10.0692
Max Act: 9.5067. Min Act: -0.1700
Data Index: 7316693 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0692. Min Range: -10.0692
Max Act: 9.5067. Min Act: -0.1700
Data Index: 5129703 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0692. Min Range: -10.0692
Max Act: 9.4442. Min Act: -0.1700
Data Index: 6873881 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0692. Min Range: -10.0692
Max Act: 9.4442. Min Act: -0.1700
Data Index: 2052367 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0692. Min Range: -10.0692
Max Act: 9.4442. Min Act: -0.1700
Data Index: 8364612 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0692. Min Range: -10.0692
Max Act: 9.3817. Min Act: -0.1700
Data Index: 3123455 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0692. Min Range: -10.0692
Max Act: 9.3817. Min Act: -0.1700
Data Index: 5112362 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0692. Min Range: -10.0692
Max Act: 9.3817. Min Act: -0.1700
Data Index: 104621 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0692. Min Range: -10.0692
Max Act: 9.3192. Min Act: -0.1700
Data Index: 5032128 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0692. Min Range: -10.0692
Max Act: 9.2567. Min Act: -0.1700
Data Index: 1556162 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0692. Min Range: -10.0692
Max Act: 9.3192. Min Act: -0.1700
Data Index: 5214390 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0692. Min Range: -10.0692
Max Act: 9.3192. Min Act: -0.1700
Data Index: 3743688 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19