Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1042 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 6.9561. Min Range: -6.9561
Max Act: 6.9561. Min Act: -0.0000
Data Index: 851739 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9561. Min Range: -6.9561
Max Act: 6.1761. Min Act: -0.0000
Data Index: 991249 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9561. Min Range: -6.9561
Max Act: 6.2450. Min Act: -0.0000
Data Index: 721511 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9561. Min Range: -6.9561
Max Act: 6.0690. Min Act: -0.0000
Data Index: 747189 (The Pile)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9561. Min Range: -6.9561
Max Act: 5.9613. Min Act: -0.0001
Data Index: 1658589 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9561. Min Range: -6.9561
Max Act: 5.9437. Min Act: -0.0000
Data Index: 335546 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9561. Min Range: -6.9561
Max Act: 5.7830. Min Act: -0.0000
Data Index: 1234132 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9561. Min Range: -6.9561
Max Act: 5.9042. Min Act: -0.0000
Data Index: 318088 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9561. Min Range: -6.9561
Max Act: 5.5584. Min Act: -0.0000
Data Index: 112771 (The Pile)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9561. Min Range: -6.9561
Max Act: 5.6857. Min Act: -0.0000
Data Index: 297040 (The Pile)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9561. Min Range: -6.9561
Max Act: 5.7291. Min Act: -0.0001
Data Index: 1947609 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9561. Min Range: -6.9561
Max Act: 5.8669. Min Act: -0.0000
Data Index: 396767 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9561. Min Range: -6.9561
Max Act: 5.4624. Min Act: -0.0000
Data Index: 1427546 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9561. Min Range: -6.9561
Max Act: 5.2727. Min Act: -0.0000
Data Index: 30079 (The Pile)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9561. Min Range: -6.9561
Max Act: 5.6045. Min Act: -0.0000
Data Index: 1645321 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9561. Min Range: -6.9561
Max Act: 5.3321. Min Act: -0.0000
Data Index: 897318 (The Pile)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9561. Min Range: -6.9561
Max Act: 5.3555. Min Act: -0.0000
Data Index: 492506 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9561. Min Range: -6.9561
Max Act: 5.3027. Min Act: -0.0000
Data Index: 781214 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9561. Min Range: -6.9561
Max Act: 5.4720. Min Act: -0.0000
Data Index: 780612 (The Pile)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9561. Min Range: -6.9561
Max Act: 5.2828. Min Act: -0.0000
Data Index: 92478 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19