Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 943 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.8616. Min Act: -0.0001
Data Index: 1978191 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.8440. Min Act: -0.0001
Data Index: 670908 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.8740. Min Act: -0.0001
Data Index: 1409969 (The Pile)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.8057. Min Act: -0.0001
Data Index: 1105272 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.8278. Min Act: -0.0001
Data Index: 1409148 (The Pile)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.6140. Min Act: -0.0002
Data Index: 1252911 (The Pile)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.6783. Min Act: -0.0001
Data Index: 926156 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.7209. Min Act: -0.0001
Data Index: 1829568 (The Pile)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.6757. Min Act: -0.0001
Data Index: 244830 (The Pile)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.7868. Min Act: -0.0001
Data Index: 1916467 (The Pile)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.6290. Min Act: -0.0001
Data Index: 136802 (The Pile)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.7927. Min Act: -0.0001
Data Index: 1356286 (The Pile)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.6380. Min Act: -0.0001
Data Index: 1096518 (The Pile)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.6680. Min Act: -0.0001
Data Index: 66956 (The Pile)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.5794. Min Act: -0.0001
Data Index: 132466 (The Pile)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.5912. Min Act: -0.0001
Data Index: 701714 (The Pile)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.6911. Min Act: -0.0001
Data Index: 1350111 (The Pile)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.4700. Min Act: -0.0001
Data Index: 925501 (The Pile)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.6074. Min Act: -0.0001
Data Index: 1336062 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8740. Min Range: -0.8740
Max Act: 0.6475. Min Act: -0.0001
Data Index: 262070 (The Pile)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19