Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2028 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.8243. Min Act: -0.1700
Data Index: 148611 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.8084. Min Act: -0.1700
Data Index: 1330018 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.7924. Min Act: -0.1700
Data Index: 121938 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.8084. Min Act: -0.1700
Data Index: 1339526 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.7765. Min Act: -0.1700
Data Index: 921855 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.7286. Min Act: -0.1700
Data Index: 290267 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.6806. Min Act: -0.1700
Data Index: 883477 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.6806. Min Act: -0.1700
Data Index: 654652 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.6646. Min Act: -0.1700
Data Index: 148665 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.6164. Min Act: -0.1700
Data Index: 912027 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.6164. Min Act: -0.1700
Data Index: 247222 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.6325. Min Act: -0.1700
Data Index: 1064288 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.6325. Min Act: -0.1700
Data Index: 1121803 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.6325. Min Act: -0.1700
Data Index: 1133070 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.6003. Min Act: -0.1700
Data Index: 1164945 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.5842. Min Act: -0.1700
Data Index: 78761 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.5681. Min Act: -0.1700
Data Index: 279783 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.5842. Min Act: -0.1700
Data Index: 816289 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.6003. Min Act: -0.1700
Data Index: 720770 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8243. Min Range: -2.8243
Max Act: 2.6003. Min Act: -0.1700
Data Index: 797843 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19