Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1971 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8907. Min Act: -0.1700
Data Index: 294721 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8749. Min Act: -0.1700
Data Index: 151097 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8590. Min Act: -0.1700
Data Index: 1353036 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8590. Min Act: -0.1700
Data Index: 627884 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8590. Min Act: -0.1700
Data Index: 383704 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8431. Min Act: -0.1700
Data Index: 1137142 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8272. Min Act: -0.1700
Data Index: 832523 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8272. Min Act: -0.1700
Data Index: 16391 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8431. Min Act: -0.1700
Data Index: 92895 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8272. Min Act: -0.1700
Data Index: 604686 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8272. Min Act: -0.1700
Data Index: 590098 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8113. Min Act: -0.1700
Data Index: 1267215 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8272. Min Act: -0.1700
Data Index: 458329 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8113. Min Act: -0.1700
Data Index: 1283715 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8431. Min Act: -0.1700
Data Index: 206754 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8113. Min Act: -0.1700
Data Index: 962075 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8272. Min Act: -0.1700
Data Index: 993071 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8113. Min Act: -0.1700
Data Index: 103559 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8113. Min Act: -0.1700
Data Index: 194030 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8907. Min Range: -2.8907
Max Act: 2.8113. Min Act: -0.1700
Data Index: 55338 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19