Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 1662 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 3.5511. Min Range: -3.5511
Max Act: 3.5511. Min Act: -0.0003
Data Index: 1744675 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5511. Min Range: -3.5511
Max Act: 3.2706. Min Act: -0.0003
Data Index: 277051 (The Pile)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5511. Min Range: -3.5511
Max Act: 3.1345. Min Act: -0.0003
Data Index: 108258 (The Pile)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5511. Min Range: -3.5511
Max Act: 3.2566. Min Act: -0.0003
Data Index: 1885779 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5511. Min Range: -3.5511
Max Act: 3.0645. Min Act: -0.0003
Data Index: 1845345 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5511. Min Range: -3.5511
Max Act: 3.0160. Min Act: -0.0003
Data Index: 415150 (The Pile)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5511. Min Range: -3.5511
Max Act: 2.8787. Min Act: -0.0003
Data Index: 662992 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5511. Min Range: -3.5511
Max Act: 2.9810. Min Act: -0.0003
Data Index: 952310 (The Pile)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5511. Min Range: -3.5511
Max Act: 2.9619. Min Act: -0.0003
Data Index: 519721 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5511. Min Range: -3.5511
Max Act: 2.9317. Min Act: -0.0003
Data Index: 1609742 (The Pile)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5511. Min Range: -3.5511
Max Act: 2.7935. Min Act: -0.0003
Data Index: 511684 (The Pile)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5511. Min Range: -3.5511
Max Act: 2.8931. Min Act: -0.0003
Data Index: 127717 (The Pile)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5511. Min Range: -3.5511
Max Act: 2.8682. Min Act: -0.0003
Data Index: 1243698 (The Pile)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5511. Min Range: -3.5511
Max Act: 2.9938. Min Act: -0.0003
Data Index: 1559372 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5511. Min Range: -3.5511
Max Act: 2.8542. Min Act: -0.0003
Data Index: 1431774 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5511. Min Range: -3.5511
Max Act: 2.8512. Min Act: -0.0003
Data Index: 1620422 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5511. Min Range: -3.5511
Max Act: 2.9741. Min Act: -0.0003
Data Index: 434425 (The Pile)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5511. Min Range: -3.5511
Max Act: 2.7267. Min Act: -0.0003
Data Index: 1034765 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5511. Min Range: -3.5511
Max Act: 2.7926. Min Act: -0.0003
Data Index: 1019042 (The Pile)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5511. Min Range: -3.5511
Max Act: 2.6713. Min Act: -0.0003
Data Index: 771062 (The Pile)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19