Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 885 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.2199. Min Act: -0.0001
Data Index: 46415 (The Pile)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.1887. Min Act: -0.0001
Data Index: 1902631 (The Pile)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.1887. Min Act: -0.0001
Data Index: 1817013 (The Pile)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.1950. Min Act: -0.0001
Data Index: 1047607 (The Pile)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.1896. Min Act: -0.0001
Data Index: 88552 (The Pile)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.1800. Min Act: -0.0001
Data Index: 29136 (The Pile)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.1803. Min Act: -0.0001
Data Index: 1896534 (The Pile)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.1742. Min Act: -0.0001
Data Index: 481021 (The Pile)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.1783. Min Act: -0.0001
Data Index: 1515231 (The Pile)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.1896. Min Act: -0.0001
Data Index: 1176528 (The Pile)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.1803. Min Act: -0.0001
Data Index: 1569458 (The Pile)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.1782. Min Act: -0.0001
Data Index: 466341 (The Pile)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.1715. Min Act: -0.0001
Data Index: 814836 (The Pile)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.1657. Min Act: -0.0001
Data Index: 780459 (The Pile)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.1699. Min Act: -0.0001
Data Index: 147289 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.1649. Min Act: -0.0001
Data Index: 1633853 (The Pile)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.1709. Min Act: -0.0001
Data Index: 933485 (The Pile)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.1650. Min Act: -0.0001
Data Index: 754995 (The Pile)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.1697. Min Act: -0.0001
Data Index: 1967106 (The Pile)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2199. Min Range: -0.2199
Max Act: 0.1746. Min Act: -0.0001
Data Index: 1590410 (The Pile)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19