Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1704 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.7046. Min Range: -1.7046
Max Act: 1.7046. Min Act: -0.0000
Data Index: 1493254 (The Pile)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7046. Min Range: -1.7046
Max Act: 1.4258. Min Act: -0.0000
Data Index: 1511 (The Pile)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7046. Min Range: -1.7046
Max Act: 1.3233. Min Act: -0.0000
Data Index: 1697422 (The Pile)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7046. Min Range: -1.7046
Max Act: 1.1003. Min Act: -0.0000
Data Index: 1821413 (The Pile)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7046. Min Range: -1.7046
Max Act: 1.2519. Min Act: -0.0000
Data Index: 165403 (The Pile)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7046. Min Range: -1.7046
Max Act: 1.1739. Min Act: -0.0000
Data Index: 1675963 (The Pile)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7046. Min Range: -1.7046
Max Act: 1.2046. Min Act: -0.0000
Data Index: 185205 (The Pile)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7046. Min Range: -1.7046
Max Act: 1.1589. Min Act: -0.0000
Data Index: 341580 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7046. Min Range: -1.7046
Max Act: 1.1400. Min Act: -0.0000
Data Index: 139575 (The Pile)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7046. Min Range: -1.7046
Max Act: 1.1184. Min Act: -0.0000
Data Index: 1162123 (The Pile)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7046. Min Range: -1.7046
Max Act: 0.9643. Min Act: -0.0000
Data Index: 980621 (The Pile)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7046. Min Range: -1.7046
Max Act: 1.0177. Min Act: -0.0000
Data Index: 168920 (The Pile)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7046. Min Range: -1.7046
Max Act: 1.0113. Min Act: -0.0000
Data Index: 757051 (The Pile)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7046. Min Range: -1.7046
Max Act: 1.0086. Min Act: -0.0000
Data Index: 512982 (The Pile)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7046. Min Range: -1.7046
Max Act: 1.1378. Min Act: -0.0000
Data Index: 604244 (The Pile)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7046. Min Range: -1.7046
Max Act: 0.9468. Min Act: -0.0000
Data Index: 897800 (The Pile)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7046. Min Range: -1.7046
Max Act: 1.0314. Min Act: -0.0001
Data Index: 994334 (The Pile)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7046. Min Range: -1.7046
Max Act: 1.0212. Min Act: -0.0000
Data Index: 172806 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7046. Min Range: -1.7046
Max Act: 0.9628. Min Act: -0.0000
Data Index: 1216524 (The Pile)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7046. Min Range: -1.7046
Max Act: 1.0189. Min Act: -0.0000
Data Index: 445812 (The Pile)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19