Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 564 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 5.2332. Min Range: -5.2332
Max Act: 5.2332. Min Act: -0.1700
Data Index: 237420 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2332. Min Range: -5.2332
Max Act: 4.9207. Min Act: -0.1700
Data Index: 42207 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2332. Min Range: -5.2332
Max Act: 4.9207. Min Act: -0.1700
Data Index: 1153480 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2332. Min Range: -5.2332
Max Act: 4.8269. Min Act: -0.1700
Data Index: 347422 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2332. Min Range: -5.2332
Max Act: 4.8269. Min Act: -0.1700
Data Index: 603054 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2332. Min Range: -5.2332
Max Act: 4.6707. Min Act: -0.1700
Data Index: 1245015 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2332. Min Range: -5.2332
Max Act: 4.7019. Min Act: -0.1700
Data Index: 267747 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2332. Min Range: -5.2332
Max Act: 4.6707. Min Act: -0.1700
Data Index: 768877 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2332. Min Range: -5.2332
Max Act: 4.6707. Min Act: -0.1700
Data Index: 123051 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2332. Min Range: -5.2332
Max Act: 4.6707. Min Act: -0.1700
Data Index: 1041732 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2332. Min Range: -5.2332
Max Act: 4.6707. Min Act: -0.1700
Data Index: 933383 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2332. Min Range: -5.2332
Max Act: 4.7019. Min Act: -0.1700
Data Index: 138698 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2332. Min Range: -5.2332
Max Act: 4.6707. Min Act: -0.1700
Data Index: 1371649 (Python Code)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2332. Min Range: -5.2332
Max Act: 4.6082. Min Act: -0.1700
Data Index: 1299603 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2332. Min Range: -5.2332
Max Act: 4.6394. Min Act: -0.1700
Data Index: 371748 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2332. Min Range: -5.2332
Max Act: 4.5769. Min Act: -0.1700
Data Index: 903307 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2332. Min Range: -5.2332
Max Act: 4.6394. Min Act: -0.1700
Data Index: 808195 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2332. Min Range: -5.2332
Max Act: 4.5769. Min Act: -0.1700
Data Index: 995908 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2332. Min Range: -5.2332
Max Act: 4.5457. Min Act: -0.1700
Data Index: 1197049 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2332. Min Range: -5.2332
Max Act: 4.5457. Min Act: -0.1700
Data Index: 235862 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19