Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2008 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.5598. Min Act: -0.1700
Data Index: 1449639 (Python Code)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.4465. Min Act: -0.1700
Data Index: 317259 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.3649. Min Act: -0.1700
Data Index: 1229919 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.3649. Min Act: -0.1700
Data Index: 712414 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.3322. Min Act: -0.1700
Data Index: 575430 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.3649. Min Act: -0.1700
Data Index: 932969 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.3158. Min Act: -0.1700
Data Index: 585643 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.3486. Min Act: -0.1700
Data Index: 1253122 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.3322. Min Act: -0.1700
Data Index: 1062156 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.2994. Min Act: -0.1700
Data Index: 1249757 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.2829. Min Act: -0.1700
Data Index: 1394215 (Python Code)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.2829. Min Act: -0.1700
Data Index: 376724 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.2829. Min Act: -0.1700
Data Index: 619752 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.2829. Min Act: -0.1700
Data Index: 579892 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.2829. Min Act: -0.1700
Data Index: 870033 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.2829. Min Act: -0.1700
Data Index: 844425 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.2664. Min Act: -0.1700
Data Index: 787334 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.2664. Min Act: -0.1700
Data Index: 310768 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.2664. Min Act: -0.1700
Data Index: 1100350 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5598. Min Range: -2.5598
Max Act: 2.2829. Min Act: -0.1700
Data Index: 659241 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19