Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1796 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.9212. Min Act: -0.1700
Data Index: 420381 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.7941. Min Act: -0.1700
Data Index: 260263 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.7303. Min Act: -0.1700
Data Index: 389773 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.6983. Min Act: -0.1700
Data Index: 1093832 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.6342. Min Act: -0.1700
Data Index: 503821 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.6503. Min Act: -0.1700
Data Index: 352801 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.6503. Min Act: -0.1700
Data Index: 399911 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.6181. Min Act: -0.1700
Data Index: 478141 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.6181. Min Act: -0.1700
Data Index: 1351545 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.6181. Min Act: -0.1700
Data Index: 1343353 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.6181. Min Act: -0.1700
Data Index: 772637 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.6020. Min Act: -0.1700
Data Index: 347235 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.6020. Min Act: -0.1700
Data Index: 174493 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.6020. Min Act: -0.1700
Data Index: 970069 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.5860. Min Act: -0.1700
Data Index: 398456 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.5860. Min Act: -0.1700
Data Index: 685932 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.5860. Min Act: -0.1700
Data Index: 255749 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.5860. Min Act: -0.1700
Data Index: 752361 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.5860. Min Act: -0.1700
Data Index: 592371 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9212. Min Range: -2.9212
Max Act: 2.5537. Min Act: -0.1700
Data Index: 753570 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19