Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2256 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.8919. Min Act: -0.0001
Data Index: 1219827 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.7569. Min Act: -0.0001
Data Index: 62874 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.7476. Min Act: -0.0001
Data Index: 509944 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.6047. Min Act: -0.0001
Data Index: 1405186 (Python Code)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.5880. Min Act: -0.0001
Data Index: 28014 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.5913. Min Act: -0.0001
Data Index: 1218727 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.5859. Min Act: -0.0001
Data Index: 1605967 (Python Code)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.5236. Min Act: -0.0001
Data Index: 464805 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.5062. Min Act: -0.0001
Data Index: 639087 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.5524. Min Act: -0.0001
Data Index: 1345344 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.4621. Min Act: -0.0001
Data Index: 153546 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.4399. Min Act: -0.0001
Data Index: 1169842 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.3962. Min Act: -0.0001
Data Index: 814717 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.3814. Min Act: -0.0001
Data Index: 1181858 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.4566. Min Act: -0.0001
Data Index: 539496 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.3636. Min Act: -0.0001
Data Index: 584804 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.4025. Min Act: -0.0001
Data Index: 600253 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.4017. Min Act: -0.0001
Data Index: 1322724 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.3553. Min Act: -0.0001
Data Index: 889006 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8919. Min Range: -1.8919
Max Act: 1.3972. Min Act: -0.0001
Data Index: 250895 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19