Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4258 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.5323. Min Act: -0.0001
Data Index: 659333 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.3251. Min Act: -0.0001
Data Index: 158127 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.4021. Min Act: -0.0001
Data Index: 865267 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.3626. Min Act: -0.0001
Data Index: 338846 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.2586. Min Act: -0.0001
Data Index: 19518 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.1460. Min Act: -0.0001
Data Index: 905853 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5323. Min Range: -2.5323
Max Act: 1.9897. Min Act: -0.0001
Data Index: 1267095 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.1423. Min Act: -0.0001
Data Index: 397687 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.0079. Min Act: -0.0001
Data Index: 32627 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5323. Min Range: -2.5323
Max Act: 1.8738. Min Act: -0.0001
Data Index: 983966 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5323. Min Range: -2.5323
Max Act: 1.9537. Min Act: -0.0001
Data Index: 1142953 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5323. Min Range: -2.5323
Max Act: 1.9619. Min Act: -0.0001
Data Index: 859370 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5323. Min Range: -2.5323
Max Act: 1.8626. Min Act: -0.0001
Data Index: 1061366 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5323. Min Range: -2.5323
Max Act: 2.0524. Min Act: -0.0001
Data Index: 910820 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5323. Min Range: -2.5323
Max Act: 1.8131. Min Act: -0.0001
Data Index: 607291 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5323. Min Range: -2.5323
Max Act: 1.8944. Min Act: -0.0001
Data Index: 483313 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5323. Min Range: -2.5323
Max Act: 1.7926. Min Act: -0.0001
Data Index: 513397 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5323. Min Range: -2.5323
Max Act: 1.7584. Min Act: -0.0001
Data Index: 663370 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5323. Min Range: -2.5323
Max Act: 1.8600. Min Act: -0.0001
Data Index: 621759 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5323. Min Range: -2.5323
Max Act: 1.8552. Min Act: -0.0001
Data Index: 630630 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19