Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2578 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.7261. Min Act: -0.0000
Data Index: 782657 (The Pile)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.3846. Min Act: -0.0000
Data Index: 1435405 (The Pile)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.3112. Min Act: -0.0000
Data Index: 1900638 (The Pile)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.1859. Min Act: 0.0000
Data Index: 1631497 (The Pile)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.2574. Min Act: -0.0000
Data Index: 1291523 (The Pile)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.2512. Min Act: 0.0001
Data Index: 32341 (The Pile)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.1909. Min Act: 0.0000
Data Index: 17709 (The Pile)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.2652. Min Act: -0.0000
Data Index: 1105143 (The Pile)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.2019. Min Act: -0.0000
Data Index: 775514 (The Pile)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.2554. Min Act: -0.0000
Data Index: 1737739 (The Pile)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.1814. Min Act: -0.0000
Data Index: 1047602 (The Pile)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.1747. Min Act: 0.0001
Data Index: 220259 (The Pile)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.1630. Min Act: 0.0001
Data Index: 1452568 (The Pile)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.1493. Min Act: 0.0000
Data Index: 1436366 (The Pile)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.0650. Min Act: -0.0000
Data Index: 636618 (The Pile)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.0675. Min Act: 0.0000
Data Index: 552486 (The Pile)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.1111. Min Act: 0.0000
Data Index: 49529 (The Pile)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.0209. Min Act: 0.0000
Data Index: 1185047 (The Pile)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.1538. Min Act: 0.0000
Data Index: 1393086 (The Pile)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7261. Min Range: -1.7261
Max Act: 1.0586. Min Act: 0.0001
Data Index: 817447 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19