Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3248 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2447. Min Range: -3.2447
Max Act: 3.2447. Min Act: -0.1700
Data Index: 3684036 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2447. Min Range: -3.2447
Max Act: 2.9135. Min Act: -0.1700
Data Index: 4115941 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2447. Min Range: -3.2447
Max Act: 2.8976. Min Act: -0.1700
Data Index: 6966272 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2447. Min Range: -3.2447
Max Act: 2.8976. Min Act: -0.1700
Data Index: 4188436 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2447. Min Range: -3.2447
Max Act: 2.8818. Min Act: -0.1700
Data Index: 6907760 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2447. Min Range: -3.2447
Max Act: 2.8818. Min Act: -0.1700
Data Index: 3119086 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2447. Min Range: -3.2447
Max Act: 2.8341. Min Act: -0.1700
Data Index: 614174 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2447. Min Range: -3.2447
Max Act: 2.8500. Min Act: -0.1700
Data Index: 6891904 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2447. Min Range: -3.2447
Max Act: 2.8182. Min Act: -0.1700
Data Index: 5588097 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2447. Min Range: -3.2447
Max Act: 2.8182. Min Act: -0.1700
Data Index: 6806540 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2447. Min Range: -3.2447
Max Act: 2.8182. Min Act: -0.1700
Data Index: 4849814 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2447. Min Range: -3.2447
Max Act: 2.8023. Min Act: -0.1697
Data Index: 6502734 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2447. Min Range: -3.2447
Max Act: 2.8023. Min Act: -0.1700
Data Index: 3095507 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2447. Min Range: -3.2447
Max Act: 2.8023. Min Act: -0.1700
Data Index: 8674015 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2447. Min Range: -3.2447
Max Act: 2.8023. Min Act: -0.1700
Data Index: 5894546 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2447. Min Range: -3.2447
Max Act: 2.7864. Min Act: -0.1700
Data Index: 3201412 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2447. Min Range: -3.2447
Max Act: 2.7545. Min Act: -0.1700
Data Index: 4755108 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2447. Min Range: -3.2447
Max Act: 2.7704. Min Act: -0.1700
Data Index: 7416909 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2447. Min Range: -3.2447
Max Act: 2.7545. Min Act: -0.1700
Data Index: 4029701 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2447. Min Range: -3.2447
Max Act: 2.7704. Min Act: -0.1700
Data Index: 3655611 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19