Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2555 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.1661. Min Range: -1.1661
Max Act: 1.1661. Min Act: -0.0000
Data Index: 1443393 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1661. Min Range: -1.1661
Max Act: 1.0642. Min Act: -0.0000
Data Index: 423773 (The Pile)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1661. Min Range: -1.1661
Max Act: 0.8700. Min Act: 0.0000
Data Index: 1145272 (The Pile)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1661. Min Range: -1.1661
Max Act: 0.8950. Min Act: -0.0000
Data Index: 1433016 (The Pile)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1661. Min Range: -1.1661
Max Act: 0.8416. Min Act: -0.0000
Data Index: 1195808 (The Pile)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1661. Min Range: -1.1661
Max Act: 0.8844. Min Act: 0.0000
Data Index: 1123265 (The Pile)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1661. Min Range: -1.1661
Max Act: 0.8759. Min Act: -0.0000
Data Index: 463836 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1661. Min Range: -1.1661
Max Act: 0.8417. Min Act: -0.0000
Data Index: 581732 (The Pile)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1661. Min Range: -1.1661
Max Act: 0.8180. Min Act: -0.0000
Data Index: 152081 (The Pile)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1661. Min Range: -1.1661
Max Act: 0.7500. Min Act: -0.0000
Data Index: 923594 (The Pile)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1661. Min Range: -1.1661
Max Act: 0.8389. Min Act: -0.0000
Data Index: 1316493 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1661. Min Range: -1.1661
Max Act: 0.8676. Min Act: 0.0000
Data Index: 74127 (The Pile)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1661. Min Range: -1.1661
Max Act: 0.8414. Min Act: -0.0000
Data Index: 415616 (The Pile)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1661. Min Range: -1.1661
Max Act: 0.8257. Min Act: 0.0000
Data Index: 1565137 (The Pile)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1661. Min Range: -1.1661
Max Act: 0.8547. Min Act: -0.0000
Data Index: 161005 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1661. Min Range: -1.1661
Max Act: 0.8278. Min Act: -0.0000
Data Index: 1285772 (The Pile)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1661. Min Range: -1.1661
Max Act: 0.8274. Min Act: -0.0000
Data Index: 346837 (The Pile)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1661. Min Range: -1.1661
Max Act: 0.8176. Min Act: -0.0000
Data Index: 1965568 (The Pile)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1661. Min Range: -1.1661
Max Act: 0.8163. Min Act: -0.0000
Data Index: 1326480 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1661. Min Range: -1.1661
Max Act: 0.8106. Min Act: -0.0000
Data Index: 1723015 (The Pile)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19