Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 863 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.5800. Min Act: -0.1700
Data Index: 16920 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.5478. Min Act: -0.1700
Data Index: 285191 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.5316. Min Act: -0.1700
Data Index: 489750 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.5316. Min Act: -0.1700
Data Index: 1018125 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.4993. Min Act: -0.1700
Data Index: 809728 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.4831. Min Act: -0.1700
Data Index: 990323 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.4831. Min Act: -0.1700
Data Index: 851524 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.4993. Min Act: -0.1700
Data Index: 912678 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.4831. Min Act: -0.1700
Data Index: 277142 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.4993. Min Act: -0.1700
Data Index: 404309 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.4831. Min Act: -0.1700
Data Index: 371333 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.4831. Min Act: -0.1700
Data Index: 1002173 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.4668. Min Act: -0.1700
Data Index: 199840 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.4668. Min Act: -0.1700
Data Index: 1267336 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.4506. Min Act: -0.1700
Data Index: 645585 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.4343. Min Act: -0.1700
Data Index: 33402 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.4343. Min Act: -0.1700
Data Index: 388069 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.4506. Min Act: -0.1700
Data Index: 1357211 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.4181. Min Act: -0.1700
Data Index: 474099 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5800. Min Range: -2.5800
Max Act: 2.4181. Min Act: -0.1700
Data Index: 729357 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19