Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.7953. Min Act: -0.1700
Data Index: 44600 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.7634. Min Act: -0.1700
Data Index: 606543 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.6675. Min Act: -0.1700
Data Index: 542512 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.6835. Min Act: -0.1700
Data Index: 210799 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.6514. Min Act: -0.1700
Data Index: 1611553 (Python Code)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.6354. Min Act: -0.1700
Data Index: 1237429 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.6354. Min Act: -0.1700
Data Index: 689329 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.6354. Min Act: -0.1700
Data Index: 802942 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.6032. Min Act: -0.1700
Data Index: 1005525 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.6193. Min Act: -0.1700
Data Index: 1508838 (Python Code)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.6032. Min Act: -0.1700
Data Index: 1095555 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.6032. Min Act: -0.1700
Data Index: 836148 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.5710. Min Act: -0.1700
Data Index: 151475 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.5710. Min Act: -0.1700
Data Index: 296462 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.5549. Min Act: -0.1700
Data Index: 246496 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.5549. Min Act: -0.1700
Data Index: 705748 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.5387. Min Act: -0.1700
Data Index: 780018 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.5226. Min Act: -0.1700
Data Index: 262017 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.5226. Min Act: -0.1700
Data Index: 402439 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7953. Min Range: -2.7953
Max Act: 2.4902. Min Act: -0.1700
Data Index: 817679 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19