Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 72 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.6829. Min Act: -0.1700
Data Index: 517519 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.6508. Min Act: -0.1700
Data Index: 1182901 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.6187. Min Act: -0.1700
Data Index: 771852 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.6187. Min Act: -0.1700
Data Index: 95677 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.5865. Min Act: -0.1700
Data Index: 913028 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.5704. Min Act: -0.1700
Data Index: 1340760 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.5704. Min Act: -0.1700
Data Index: 1221280 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.5865. Min Act: -0.1700
Data Index: 271013 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.5704. Min Act: -0.1700
Data Index: 605086 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.5704. Min Act: -0.1700
Data Index: 810623 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.5704. Min Act: -0.1700
Data Index: 79131 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.5704. Min Act: -0.1700
Data Index: 387759 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.5543. Min Act: -0.1700
Data Index: 1022234 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.5543. Min Act: -0.1700
Data Index: 834698 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.5543. Min Act: -0.1700
Data Index: 1280374 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.5543. Min Act: -0.1700
Data Index: 552740 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.5381. Min Act: -0.1700
Data Index: 1274810 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.5381. Min Act: -0.1700
Data Index: 1076234 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.5543. Min Act: -0.1700
Data Index: 208613 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6829. Min Range: -2.6829
Max Act: 2.5704. Min Act: -0.1700
Data Index: 157110 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19