Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 939 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.5207. Min Act: -0.1700
Data Index: 1274540 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.4883. Min Act: -0.1700
Data Index: 952322 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.5045. Min Act: -0.1700
Data Index: 47622 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.4883. Min Act: -0.1700
Data Index: 426005 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.4883. Min Act: -0.1700
Data Index: 799457 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.4721. Min Act: -0.1700
Data Index: 30834 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.4558. Min Act: -0.1700
Data Index: 902968 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.4558. Min Act: -0.1700
Data Index: 444512 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.4721. Min Act: -0.1700
Data Index: 904896 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.4721. Min Act: -0.1700
Data Index: 695804 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.4721. Min Act: -0.1700
Data Index: 682445 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.4721. Min Act: -0.1700
Data Index: 567663 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.4558. Min Act: -0.1700
Data Index: 939385 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.4558. Min Act: -0.1700
Data Index: 728663 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.4396. Min Act: -0.1700
Data Index: 126200 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.4558. Min Act: -0.1700
Data Index: 838121 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.4558. Min Act: -0.1700
Data Index: 371706 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.4558. Min Act: -0.1700
Data Index: 818553 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.4558. Min Act: -0.1700
Data Index: 438015 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5207. Min Range: -2.5207
Max Act: 2.4558. Min Act: -0.1700
Data Index: 315250 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19