Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 557 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.8864. Min Range: -1.8864
Max Act: 1.6237. Min Act: -0.0001
Data Index: 1037101 (The Pile)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8864. Min Range: -1.8864
Max Act: 1.8864. Min Act: -0.0001
Data Index: 1594552 (The Pile)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8864. Min Range: -1.8864
Max Act: 1.5574. Min Act: -0.0001
Data Index: 1898602 (The Pile)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8864. Min Range: -1.8864
Max Act: 1.6418. Min Act: -0.0001
Data Index: 1307209 (The Pile)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8864. Min Range: -1.8864
Max Act: 1.6544. Min Act: -0.0001
Data Index: 837663 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8864. Min Range: -1.8864
Max Act: 1.4741. Min Act: -0.0001
Data Index: 1394726 (The Pile)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8864. Min Range: -1.8864
Max Act: 1.3028. Min Act: -0.0001
Data Index: 598314 (The Pile)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8864. Min Range: -1.8864
Max Act: 1.4075. Min Act: -0.0001
Data Index: 49415 (The Pile)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8864. Min Range: -1.8864
Max Act: 1.5433. Min Act: -0.0001
Data Index: 1083873 (The Pile)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8864. Min Range: -1.8864
Max Act: 1.5689. Min Act: -0.0001
Data Index: 679180 (The Pile)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8864. Min Range: -1.8864
Max Act: 1.4411. Min Act: -0.0001
Data Index: 1428341 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8864. Min Range: -1.8864
Max Act: 1.4112. Min Act: -0.0001
Data Index: 1041203 (The Pile)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8864. Min Range: -1.8864
Max Act: 1.0800. Min Act: -0.0001
Data Index: 538042 (The Pile)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8864. Min Range: -1.8864
Max Act: 1.1392. Min Act: -0.0001
Data Index: 598394 (The Pile)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8864. Min Range: -1.8864
Max Act: 1.3014. Min Act: -0.0001
Data Index: 33224 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8864. Min Range: -1.8864
Max Act: 1.3357. Min Act: -0.0001
Data Index: 700642 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8864. Min Range: -1.8864
Max Act: 1.2277. Min Act: -0.0001
Data Index: 326109 (The Pile)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8864. Min Range: -1.8864
Max Act: 1.2174. Min Act: -0.0001
Data Index: 907665 (The Pile)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8864. Min Range: -1.8864
Max Act: 0.9971. Min Act: -0.0001
Data Index: 333266 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8864. Min Range: -1.8864
Max Act: 1.1595. Min Act: -0.0001
Data Index: 1489614 (The Pile)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19