Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2022 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 2.6223. Min Range: -2.6223
Max Act: 2.6223. Min Act: -0.0000
Data Index: 228 (The Pile)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6223. Min Range: -2.6223
Max Act: 2.3994. Min Act: -0.0000
Data Index: 903535 (The Pile)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6223. Min Range: -2.6223
Max Act: 2.2049. Min Act: -0.0000
Data Index: 21246 (The Pile)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6223. Min Range: -2.6223
Max Act: 2.1946. Min Act: -0.0000
Data Index: 669943 (The Pile)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6223. Min Range: -2.6223
Max Act: 1.9746. Min Act: -0.0000
Data Index: 743912 (The Pile)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6223. Min Range: -2.6223
Max Act: 1.8600. Min Act: -0.0000
Data Index: 1014215 (The Pile)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6223. Min Range: -2.6223
Max Act: 2.0587. Min Act: -0.0000
Data Index: 1858312 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6223. Min Range: -2.6223
Max Act: 1.8409. Min Act: -0.0000
Data Index: 1680364 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6223. Min Range: -2.6223
Max Act: 1.8435. Min Act: -0.0000
Data Index: 1005351 (The Pile)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6223. Min Range: -2.6223
Max Act: 1.9400. Min Act: -0.0000
Data Index: 42946 (The Pile)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6223. Min Range: -2.6223
Max Act: 1.6914. Min Act: -0.0000
Data Index: 773336 (The Pile)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6223. Min Range: -2.6223
Max Act: 1.7644. Min Act: -0.0000
Data Index: 1235620 (The Pile)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6223. Min Range: -2.6223
Max Act: 1.7725. Min Act: -0.0000
Data Index: 1260619 (The Pile)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6223. Min Range: -2.6223
Max Act: 1.9725. Min Act: -0.0000
Data Index: 654291 (The Pile)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6223. Min Range: -2.6223
Max Act: 1.6728. Min Act: -0.0000
Data Index: 1508389 (The Pile)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6223. Min Range: -2.6223
Max Act: 1.7002. Min Act: -0.0000
Data Index: 1569470 (The Pile)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6223. Min Range: -2.6223
Max Act: 1.6985. Min Act: -0.0000
Data Index: 1728656 (The Pile)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6223. Min Range: -2.6223
Max Act: 1.5985. Min Act: -0.0000
Data Index: 1062667 (The Pile)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6223. Min Range: -2.6223
Max Act: 1.6556. Min Act: -0.0000
Data Index: 1728386 (The Pile)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6223. Min Range: -2.6223
Max Act: 1.8470. Min Act: -0.0000
Data Index: 409868 (The Pile)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19