Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 792 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.7544. Min Act: -0.1700
Data Index: 593241 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.5357. Min Act: -0.1700
Data Index: 922556 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.5357. Min Act: -0.1700
Data Index: 658610 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.4732. Min Act: -0.1700
Data Index: 1391817 (Python Code)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.4732. Min Act: -0.1700
Data Index: 650619 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.4732. Min Act: -0.1700
Data Index: 205993 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.4419. Min Act: -0.1700
Data Index: 1129786 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.4106. Min Act: -0.1700
Data Index: 941897 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.4106. Min Act: -0.1700
Data Index: 585594 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.4419. Min Act: -0.1700
Data Index: 782822 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.4419. Min Act: -0.1700
Data Index: 184287 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.4106. Min Act: -0.1700
Data Index: 1063798 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.3794. Min Act: -0.1700
Data Index: 878689 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.3794. Min Act: -0.1700
Data Index: 647581 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.4106. Min Act: -0.1700
Data Index: 864846 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.3794. Min Act: -0.1700
Data Index: 195936 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.3481. Min Act: -0.1700
Data Index: 209226 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.3794. Min Act: -0.1700
Data Index: 574914 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.3481. Min Act: -0.1700
Data Index: 59487 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7544. Min Range: -4.7544
Max Act: 4.3481. Min Act: -0.1700
Data Index: 773349 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19