Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 70 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.3349. Min Act: -0.1700
Data Index: 486001 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.2691. Min Act: -0.1700
Data Index: 1084874 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.2526. Min Act: -0.1700
Data Index: 483348 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.2196. Min Act: -0.1700
Data Index: 305201 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.1698. Min Act: -0.1700
Data Index: 497112 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.1864. Min Act: -0.1700
Data Index: 70521 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.1698. Min Act: -0.1700
Data Index: 1433046 (Python Code)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.1698. Min Act: -0.1700
Data Index: 1498366 (Python Code)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.1864. Min Act: -0.1700
Data Index: 566373 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.1532. Min Act: -0.1700
Data Index: 1492984 (Python Code)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.1365. Min Act: -0.1700
Data Index: 1532566 (Python Code)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.1365. Min Act: -0.1700
Data Index: 1005678 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.1198. Min Act: -0.1700
Data Index: 433116 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.1031. Min Act: -0.1700
Data Index: 625733 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.1365. Min Act: -0.1700
Data Index: 935818 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.1198. Min Act: -0.1700
Data Index: 450465 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.1031. Min Act: -0.1700
Data Index: 535712 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.0864. Min Act: -0.1700
Data Index: 1490661 (Python Code)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.0864. Min Act: -0.1700
Data Index: 735299 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3349. Min Range: -2.3349
Max Act: 2.0864. Min Act: -0.1700
Data Index: 908847 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19