Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 20 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.8996. Min Act: -0.1700
Data Index: 1236994 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.8837. Min Act: -0.1700
Data Index: 285010 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.8678. Min Act: -0.1700
Data Index: 74524 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.8360. Min Act: -0.1700
Data Index: 306598 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.8360. Min Act: -0.1700
Data Index: 1304231 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.8360. Min Act: -0.1700
Data Index: 669409 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.8360. Min Act: -0.1700
Data Index: 960551 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.8519. Min Act: -0.1700
Data Index: 867715 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.8360. Min Act: -0.1700
Data Index: 1105032 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.7723. Min Act: -0.1700
Data Index: 1137096 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.7883. Min Act: -0.1700
Data Index: 830759 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.7723. Min Act: -0.1700
Data Index: 327790 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.7723. Min Act: -0.1700
Data Index: 614314 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.7883. Min Act: -0.1700
Data Index: 1082278 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.7564. Min Act: -0.1700
Data Index: 1078601 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.7723. Min Act: -0.1700
Data Index: 1222605 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.7883. Min Act: -0.1700
Data Index: 407215 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.7404. Min Act: -0.1700
Data Index: 1047808 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.7564. Min Act: -0.1700
Data Index: 986251 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8996. Min Range: -2.8996
Max Act: 2.7564. Min Act: -0.1700
Data Index: 515333 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19