Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 191 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.5810. Min Act: -0.1700
Data Index: 215205 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.3622. Min Act: -0.1700
Data Index: 940069 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.3622. Min Act: -0.1700
Data Index: 617298 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.3310. Min Act: -0.1700
Data Index: 1533461 (Python Code)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.2997. Min Act: -0.1700
Data Index: 129616 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.3622. Min Act: -0.1700
Data Index: 1033014 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.3310. Min Act: -0.1700
Data Index: 586628 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.2685. Min Act: -0.1700
Data Index: 653110 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.1747. Min Act: -0.1700
Data Index: 495790 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.2685. Min Act: -0.1700
Data Index: 454067 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.2997. Min Act: -0.1700
Data Index: 1305842 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.2997. Min Act: -0.1700
Data Index: 84628 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.2685. Min Act: -0.1700
Data Index: 223605 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.2060. Min Act: -0.1700
Data Index: 1304293 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.2372. Min Act: -0.1700
Data Index: 1006337 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.2997. Min Act: -0.1700
Data Index: 54527 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.2997. Min Act: -0.1700
Data Index: 1207632 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.2060. Min Act: -0.1700
Data Index: 399790 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.2997. Min Act: -0.1700
Data Index: 757792 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5810. Min Range: -4.5810
Max Act: 4.2997. Min Act: -0.1700
Data Index: 1128348 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19