Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3081 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6209. Min Range: -8.6209
Max Act: 8.6209. Min Act: -0.1700
Data Index: 7996928 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6209. Min Range: -8.6209
Max Act: 8.4334. Min Act: -0.1700
Data Index: 7291628 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6209. Min Range: -8.6209
Max Act: 8.2459. Min Act: -0.1700
Data Index: 1630904 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6209. Min Range: -8.6209
Max Act: 8.1834. Min Act: -0.1700
Data Index: 732752 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6209. Min Range: -8.6209
Max Act: 8.1834. Min Act: -0.1700
Data Index: 1697771 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6209. Min Range: -8.6209
Max Act: 8.1834. Min Act: -0.1700
Data Index: 6588138 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6209. Min Range: -8.6209
Max Act: 8.1834. Min Act: -0.1700
Data Index: 3485671 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6209. Min Range: -8.6209
Max Act: 8.1834. Min Act: -0.1700
Data Index: 6196627 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6209. Min Range: -8.6209
Max Act: 8.0584. Min Act: -0.1700
Data Index: 2589998 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6209. Min Range: -8.6209
Max Act: 8.1209. Min Act: -0.1700
Data Index: 545383 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6209. Min Range: -8.6209
Max Act: 8.0584. Min Act: -0.1700
Data Index: 1563601 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6209. Min Range: -8.6209
Max Act: 8.1209. Min Act: -0.1700
Data Index: 1207346 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6209. Min Range: -8.6209
Max Act: 8.1209. Min Act: -0.1700
Data Index: 8155899 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6209. Min Range: -8.6209
Max Act: 8.1209. Min Act: -0.1700
Data Index: 2852426 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6209. Min Range: -8.6209
Max Act: 8.0584. Min Act: -0.1700
Data Index: 3989583 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6209. Min Range: -8.6209
Max Act: 8.0584. Min Act: -0.1700
Data Index: 1885968 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6209. Min Range: -8.6209
Max Act: 8.0584. Min Act: -0.1700
Data Index: 7640346 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6209. Min Range: -8.6209
Max Act: 7.9959. Min Act: -0.1700
Data Index: 6243988 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6209. Min Range: -8.6209
Max Act: 7.9959. Min Act: -0.1700
Data Index: 3774106 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6209. Min Range: -8.6209
Max Act: 7.9959. Min Act: -0.1700
Data Index: 742244 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19