Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 115 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.5674. Min Act: -0.1700
Data Index: 1066006 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.5513. Min Act: -0.1700
Data Index: 41376 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.5028. Min Act: -0.1700
Data Index: 239141 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.4866. Min Act: -0.1700
Data Index: 849463 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.4542. Min Act: -0.1700
Data Index: 472766 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.4704. Min Act: -0.1700
Data Index: 608794 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.4542. Min Act: -0.1700
Data Index: 537142 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.4379. Min Act: -0.1700
Data Index: 555775 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.4216. Min Act: -0.1700
Data Index: 744680 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.4053. Min Act: -0.1700
Data Index: 463396 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.3890. Min Act: -0.1700
Data Index: 365099 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.3890. Min Act: -0.1700
Data Index: 109860 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.4053. Min Act: -0.1700
Data Index: 1335388 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.3727. Min Act: -0.1700
Data Index: 1122036 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.3727. Min Act: -0.1700
Data Index: 368381 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.3727. Min Act: -0.1700
Data Index: 974646 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.3890. Min Act: -0.1700
Data Index: 505232 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.3727. Min Act: -0.1700
Data Index: 677523 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.3727. Min Act: -0.1700
Data Index: 551734 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5674. Min Range: -2.5674
Max Act: 2.3563. Min Act: -0.1700
Data Index: 487795 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19