Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 140 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.7490. Min Act: -0.1700
Data Index: 388555 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.7170. Min Act: -0.1700
Data Index: 1046489 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.6850. Min Act: -0.1700
Data Index: 157287 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.6690. Min Act: -0.1700
Data Index: 1235063 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.6690. Min Act: -0.1700
Data Index: 116245 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.6850. Min Act: -0.1700
Data Index: 1187947 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.6530. Min Act: -0.1700
Data Index: 717426 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.6369. Min Act: -0.1700
Data Index: 476628 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.6048. Min Act: -0.1699
Data Index: 529483 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.6208. Min Act: -0.1700
Data Index: 405575 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.6208. Min Act: -0.1700
Data Index: 429974 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.6369. Min Act: -0.1700
Data Index: 458380 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.6048. Min Act: -0.1700
Data Index: 1606413 (Python Code)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.6048. Min Act: -0.1700
Data Index: 753021 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.6208. Min Act: -0.1700
Data Index: 406494 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.6048. Min Act: -0.1700
Data Index: 470415 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.6048. Min Act: -0.1700
Data Index: 476909 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.5887. Min Act: -0.1700
Data Index: 517216 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.5726. Min Act: -0.1700
Data Index: 626393 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7490. Min Range: -2.7490
Max Act: 2.5726. Min Act: -0.1700
Data Index: 1143449 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19