Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2070 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.2207. Min Range: -2.2207
Max Act: 2.1825. Min Act: 0.0001
Data Index: 481325 (The Pile)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2207. Min Range: -2.2207
Max Act: 2.0976. Min Act: 0.0002
Data Index: 578958 (The Pile)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2207. Min Range: -2.2207
Max Act: 2.2207. Min Act: 0.0002
Data Index: 1835295 (The Pile)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2207. Min Range: -2.2207
Max Act: 2.1110. Min Act: 0.0002
Data Index: 380643 (The Pile)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2207. Min Range: -2.2207
Max Act: 1.9662. Min Act: 0.0001
Data Index: 1362198 (The Pile)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2207. Min Range: -2.2207
Max Act: 1.8722. Min Act: 0.0000
Data Index: 1110331 (The Pile)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2207. Min Range: -2.2207
Max Act: 1.9562. Min Act: 0.0001
Data Index: 791286 (The Pile)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2207. Min Range: -2.2207
Max Act: 2.0192. Min Act: 0.0002
Data Index: 52723 (The Pile)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2207. Min Range: -2.2207
Max Act: 1.8865. Min Act: 0.0000
Data Index: 148269 (The Pile)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2207. Min Range: -2.2207
Max Act: 1.8100. Min Act: 0.0001
Data Index: 1543989 (The Pile)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2207. Min Range: -2.2207
Max Act: 1.8031. Min Act: 0.0001
Data Index: 1898611 (The Pile)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2207. Min Range: -2.2207
Max Act: 1.7843. Min Act: 0.0000
Data Index: 1597169 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2207. Min Range: -2.2207
Max Act: 1.8748. Min Act: 0.0002
Data Index: 624413 (The Pile)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2207. Min Range: -2.2207
Max Act: 1.9074. Min Act: 0.0002
Data Index: 789972 (The Pile)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2207. Min Range: -2.2207
Max Act: 1.8713. Min Act: 0.0002
Data Index: 1124095 (The Pile)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2207. Min Range: -2.2207
Max Act: 1.8764. Min Act: 0.0001
Data Index: 636040 (The Pile)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2207. Min Range: -2.2207
Max Act: 1.7567. Min Act: 0.0001
Data Index: 676571 (The Pile)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2207. Min Range: -2.2207
Max Act: 1.8473. Min Act: 0.0001
Data Index: 1054782 (The Pile)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2207. Min Range: -2.2207
Max Act: 1.7384. Min Act: 0.0002
Data Index: 82976 (The Pile)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2207. Min Range: -2.2207
Max Act: 1.8428. Min Act: 0.0001
Data Index: 1555449 (The Pile)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19