Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 170 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5866. Min Range: -8.5866
Max Act: 8.5866. Min Act: -0.1700
Data Index: 3303836 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5866. Min Range: -8.5866
Max Act: 8.2116. Min Act: -0.1700
Data Index: 2780432 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5866. Min Range: -8.5866
Max Act: 8.1491. Min Act: -0.1700
Data Index: 3659734 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5866. Min Range: -8.5866
Max Act: 8.1491. Min Act: -0.1700
Data Index: 7178438 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5866. Min Range: -8.5866
Max Act: 8.0866. Min Act: -0.1700
Data Index: 7132522 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5866. Min Range: -8.5866
Max Act: 8.0241. Min Act: -0.1700
Data Index: 6017596 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5866. Min Range: -8.5866
Max Act: 8.0241. Min Act: -0.1700
Data Index: 1462630 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5866. Min Range: -8.5866
Max Act: 8.0241. Min Act: -0.1700
Data Index: 1456234 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5866. Min Range: -8.5866
Max Act: 7.9616. Min Act: -0.1700
Data Index: 845874 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5866. Min Range: -8.5866
Max Act: 7.9616. Min Act: -0.1700
Data Index: 4461698 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5866. Min Range: -8.5866
Max Act: 7.9616. Min Act: -0.1700
Data Index: 7083263 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5866. Min Range: -8.5866
Max Act: 7.8991. Min Act: -0.1700
Data Index: 4082129 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5866. Min Range: -8.5866
Max Act: 7.8991. Min Act: -0.1700
Data Index: 744995 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5866. Min Range: -8.5866
Max Act: 7.8991. Min Act: -0.1700
Data Index: 3040351 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5866. Min Range: -8.5866
Max Act: 7.8991. Min Act: -0.1700
Data Index: 7208921 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5866. Min Range: -8.5866
Max Act: 7.8991. Min Act: -0.1700
Data Index: 1027076 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5866. Min Range: -8.5866
Max Act: 7.8991. Min Act: -0.1700
Data Index: 7139588 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5866. Min Range: -8.5866
Max Act: 7.8366. Min Act: -0.1700
Data Index: 6112342 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5866. Min Range: -8.5866
Max Act: 7.8366. Min Act: -0.1700
Data Index: 2834414 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5866. Min Range: -8.5866
Max Act: 7.8991. Min Act: -0.1700
Data Index: 4788007 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19