Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.5299. Min Act: -0.1700
Data Index: 294166 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.4986. Min Act: -0.1700
Data Index: 7392326 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.4986. Min Act: -0.1700
Data Index: 8571726 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.4986. Min Act: -0.1700
Data Index: 4718855 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.4361. Min Act: -0.1700
Data Index: 1679050 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.4361. Min Act: -0.1695
Data Index: 878310 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.4049. Min Act: -0.1700
Data Index: 8614964 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.3736. Min Act: -0.1700
Data Index: 7392323 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.3424. Min Act: -0.1700
Data Index: 8479613 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.3424. Min Act: -0.1700
Data Index: 733751 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.3111. Min Act: -0.1700
Data Index: 2186147 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.3111. Min Act: -0.1700
Data Index: 703941 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.3111. Min Act: -0.1700
Data Index: 2608457 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.3111. Min Act: -0.1700
Data Index: 6064284 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.2799. Min Act: -0.1700
Data Index: 7392328 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.2799. Min Act: -0.1700
Data Index: 1551732 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.2799. Min Act: -0.1700
Data Index: 434651 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.2799. Min Act: -0.1700
Data Index: 1312818 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.2799. Min Act: -0.1700
Data Index: 1527587 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5299. Min Range: -5.5299
Max Act: 5.2799. Min Act: -0.1700
Data Index: 2829904 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19