Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3087 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.4440. Min Act: -0.1700
Data Index: 971676 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.4440. Min Act: -0.1700
Data Index: 2252571 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.3815. Min Act: -0.1700
Data Index: 4108891 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.3502. Min Act: -0.1700
Data Index: 4906191 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.3502. Min Act: -0.1700
Data Index: 2887791 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.3190. Min Act: -0.1700
Data Index: 5256511 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.2877. Min Act: -0.1700
Data Index: 6679117 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.2877. Min Act: -0.1700
Data Index: 7623120 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.2877. Min Act: -0.1700
Data Index: 3702729 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.2252. Min Act: -0.1700
Data Index: 836929 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.2565. Min Act: -0.1700
Data Index: 8497257 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.2565. Min Act: -0.1700
Data Index: 1959604 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.2565. Min Act: -0.1700
Data Index: 7744619 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.2565. Min Act: -0.1700
Data Index: 2276323 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.2565. Min Act: -0.1700
Data Index: 893161 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.2565. Min Act: -0.1700
Data Index: 6429218 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.2565. Min Act: -0.1700
Data Index: 7422022 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.2252. Min Act: -0.1700
Data Index: 354170 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.2252. Min Act: -0.1700
Data Index: 5249167 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4440. Min Range: -5.4440
Max Act: 5.1940. Min Act: -0.1700
Data Index: 8585747 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19