Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 92 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.6967. Min Act: -0.1700
Data Index: 1270156 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.6486. Min Act: -0.1700
Data Index: 538450 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.6004. Min Act: -0.1700
Data Index: 643822 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.6165. Min Act: -0.1700
Data Index: 529891 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.5682. Min Act: -0.1700
Data Index: 1351966 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.5843. Min Act: -0.1700
Data Index: 344491 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.5843. Min Act: -0.1700
Data Index: 23091 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.5843. Min Act: -0.1700
Data Index: 1328690 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.5843. Min Act: -0.1700
Data Index: 1023984 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.5197. Min Act: -0.1700
Data Index: 1197394 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.5359. Min Act: -0.1700
Data Index: 884425 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.5197. Min Act: -0.1700
Data Index: 1203263 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.5359. Min Act: -0.1700
Data Index: 370909 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.5197. Min Act: -0.1700
Data Index: 480681 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.5197. Min Act: -0.1700
Data Index: 826029 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.5197. Min Act: -0.1700
Data Index: 377854 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.5359. Min Act: -0.1700
Data Index: 921873 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.5359. Min Act: -0.1700
Data Index: 478779 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.5197. Min Act: -0.1700
Data Index: 610285 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6967. Min Range: -2.6967
Max Act: 2.5359. Min Act: -0.1700
Data Index: 974998 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19