Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 900 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.4200. Min Act: -0.1700
Data Index: 1160875 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.3219. Min Act: -0.1700
Data Index: 569350 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.3219. Min Act: -0.1700
Data Index: 170078 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.3055. Min Act: -0.1700
Data Index: 1233867 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.2890. Min Act: -0.1700
Data Index: 37530 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.2725. Min Act: -0.1700
Data Index: 706882 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.2725. Min Act: -0.1700
Data Index: 1312326 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.2725. Min Act: -0.1700
Data Index: 1101724 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.2395. Min Act: -0.1700
Data Index: 107985 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.2395. Min Act: -0.1700
Data Index: 1228370 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.2395. Min Act: -0.1700
Data Index: 1253849 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.2395. Min Act: -0.1700
Data Index: 698188 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.2230. Min Act: -0.1700
Data Index: 1265927 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.2064. Min Act: -0.1700
Data Index: 1195043 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.1899. Min Act: -0.1700
Data Index: 1044824 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.2064. Min Act: -0.1700
Data Index: 224057 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.1899. Min Act: -0.1700
Data Index: 158509 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.1899. Min Act: -0.1700
Data Index: 1338418 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.1733. Min Act: -0.1700
Data Index: 52093 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4200. Min Range: -2.4200
Max Act: 2.1733. Min Act: -0.1700
Data Index: 693424 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19