Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2842 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.5187. Min Range: -1.5187
Max Act: 1.5187. Min Act: -0.0001
Data Index: 1228392 (The Pile)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5187. Min Range: -1.5187
Max Act: 1.4141. Min Act: -0.0001
Data Index: 521113 (The Pile)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5187. Min Range: -1.5187
Max Act: 1.2391. Min Act: -0.0001
Data Index: 1144641 (The Pile)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5187. Min Range: -1.5187
Max Act: 1.2123. Min Act: -0.0001
Data Index: 856623 (The Pile)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5187. Min Range: -1.5187
Max Act: 1.1125. Min Act: -0.0001
Data Index: 1095769 (The Pile)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5187. Min Range: -1.5187
Max Act: 1.1088. Min Act: -0.0001
Data Index: 1102031 (The Pile)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5187. Min Range: -1.5187
Max Act: 1.0761. Min Act: -0.0001
Data Index: 1975794 (The Pile)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5187. Min Range: -1.5187
Max Act: 0.9613. Min Act: -0.0001
Data Index: 1939291 (The Pile)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5187. Min Range: -1.5187
Max Act: 1.0415. Min Act: -0.0001
Data Index: 764245 (The Pile)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5187. Min Range: -1.5187
Max Act: 1.0599. Min Act: -0.0001
Data Index: 486488 (The Pile)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5187. Min Range: -1.5187
Max Act: 1.0061. Min Act: -0.0001
Data Index: 733768 (The Pile)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5187. Min Range: -1.5187
Max Act: 0.9760. Min Act: -0.0001
Data Index: 455874 (The Pile)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5187. Min Range: -1.5187
Max Act: 0.9579. Min Act: -0.0001
Data Index: 557454 (The Pile)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5187. Min Range: -1.5187
Max Act: 0.9844. Min Act: -0.0001
Data Index: 1183385 (The Pile)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5187. Min Range: -1.5187
Max Act: 1.0299. Min Act: -0.0001
Data Index: 162411 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5187. Min Range: -1.5187
Max Act: 0.9375. Min Act: -0.0001
Data Index: 1760735 (The Pile)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5187. Min Range: -1.5187
Max Act: 0.9700. Min Act: -0.0001
Data Index: 244601 (The Pile)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5187. Min Range: -1.5187
Max Act: 0.9927. Min Act: -0.0001
Data Index: 1575444 (The Pile)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5187. Min Range: -1.5187
Max Act: 0.9268. Min Act: -0.0001
Data Index: 921582 (The Pile)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5187. Min Range: -1.5187
Max Act: 0.9088. Min Act: -0.0001
Data Index: 1268874 (The Pile)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19