Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 98 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.9860. Min Act: -0.1700
Data Index: 302340 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.8610. Min Act: -0.1700
Data Index: 292866 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.7672. Min Act: -0.1700
Data Index: 1031124 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.7360. Min Act: -0.1700
Data Index: 873857 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.7360. Min Act: -0.1700
Data Index: 688919 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.7360. Min Act: -0.1700
Data Index: 378389 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.7360. Min Act: -0.1700
Data Index: 1101321 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.7047. Min Act: -0.1700
Data Index: 963605 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.7672. Min Act: -0.1700
Data Index: 873794 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.6735. Min Act: -0.1700
Data Index: 991568 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.6735. Min Act: -0.1700
Data Index: 1100146 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.6735. Min Act: -0.1700
Data Index: 261876 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.7047. Min Act: -0.1700
Data Index: 1021893 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.6735. Min Act: -0.1700
Data Index: 203803 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.7047. Min Act: -0.1700
Data Index: 1057659 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.6110. Min Act: -0.1700
Data Index: 1256916 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.6110. Min Act: -0.1700
Data Index: 11264 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.6735. Min Act: -0.1700
Data Index: 49630 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.6422. Min Act: -0.1700
Data Index: 375778 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9860. Min Range: -4.9860
Max Act: 4.6110. Min Act: -0.1700
Data Index: 133403 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19