Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.4361. Min Act: -0.1700
Data Index: 5199185 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.4361. Min Act: -0.1700
Data Index: 3543944 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.3423. Min Act: -0.1700
Data Index: 8429868 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.3111. Min Act: -0.1700
Data Index: 7292517 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.3111. Min Act: -0.1700
Data Index: 8559915 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.3111. Min Act: -0.1697
Data Index: 5129944 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.2798. Min Act: -0.1700
Data Index: 485195 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.2798. Min Act: -0.1700
Data Index: 8146534 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.2798. Min Act: -0.1699
Data Index: 3611008 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.2798. Min Act: -0.1697
Data Index: 7974128 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.2798. Min Act: -0.1700
Data Index: 7795541 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.2173. Min Act: -0.1700
Data Index: 449099 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.2486. Min Act: -0.1699
Data Index: 6625020 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.2173. Min Act: -0.1700
Data Index: 6343150 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.2486. Min Act: -0.1700
Data Index: 5710977 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.2486. Min Act: -0.1700
Data Index: 2781108 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.2173. Min Act: -0.1700
Data Index: 324549 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.2173. Min Act: -0.1694
Data Index: 8240438 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.2173. Min Act: -0.1700
Data Index: 8388694 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4361. Min Range: -5.4361
Max Act: 5.2173. Min Act: -0.1700
Data Index: 4574325 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19