Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 166 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.3837. Min Act: -0.1700
Data Index: 913041 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.3837. Min Act: -0.1700
Data Index: 138310 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.3837. Min Act: -0.1700
Data Index: 485080 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.3212. Min Act: -0.1700
Data Index: 493421 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.3524. Min Act: -0.1700
Data Index: 134990 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.3524. Min Act: -0.1700
Data Index: 1250043 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.3212. Min Act: -0.1700
Data Index: 702499 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.3212. Min Act: -0.1700
Data Index: 377512 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.3212. Min Act: -0.1700
Data Index: 14336 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.3212. Min Act: -0.1700
Data Index: 656210 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.3212. Min Act: -0.1700
Data Index: 689848 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.3212. Min Act: -0.1700
Data Index: 745743 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.3212. Min Act: -0.1700
Data Index: 1320611 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.3212. Min Act: -0.1700
Data Index: 297077 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.3212. Min Act: -0.1700
Data Index: 1337456 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.2899. Min Act: -0.1700
Data Index: 394908 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.2587. Min Act: -0.1700
Data Index: 60528 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.2899. Min Act: -0.1700
Data Index: 37034 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.2899. Min Act: -0.1700
Data Index: 1164206 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3837. Min Range: -4.3837
Max Act: 4.2899. Min Act: -0.1700
Data Index: 962683 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19