Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1996 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.1779. Min Act: -0.1700
Data Index: 1188716 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.1779. Min Act: -0.1700
Data Index: 985815 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.1446. Min Act: -0.1700
Data Index: 689656 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.1446. Min Act: -0.1700
Data Index: 676469 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.1446. Min Act: -0.1700
Data Index: 651560 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.1446. Min Act: -0.1700
Data Index: 696164 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.1446. Min Act: -0.1700
Data Index: 156504 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.1113. Min Act: -0.1700
Data Index: 680587 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.1113. Min Act: -0.1700
Data Index: 868795 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.0945. Min Act: -0.1700
Data Index: 309876 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.1113. Min Act: -0.1700
Data Index: 1241800 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.1113. Min Act: -0.1700
Data Index: 927770 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.0945. Min Act: -0.1700
Data Index: 640736 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.1113. Min Act: -0.1700
Data Index: 108178 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.0778. Min Act: -0.1700
Data Index: 997139 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.0945. Min Act: -0.1700
Data Index: 1663 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.0945. Min Act: -0.1700
Data Index: 307877 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.0610. Min Act: -0.1700
Data Index: 565013 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.0778. Min Act: -0.1700
Data Index: 329883 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1779. Min Range: -2.1779
Max Act: 2.0778. Min Act: -0.1700
Data Index: 1061069 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19