Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3144 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.3672. Min Range: -2.3672
Max Act: 2.3378. Min Act: -0.0001
Data Index: 1335321 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3672. Min Range: -2.3672
Max Act: 2.2083. Min Act: -0.0001
Data Index: 920317 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3672. Min Range: -2.3672
Max Act: 2.3672. Min Act: -0.0001
Data Index: 104723 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3672. Min Range: -2.3672
Max Act: 2.2226. Min Act: -0.0001
Data Index: 287387 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3672. Min Range: -2.3672
Max Act: 2.1373. Min Act: -0.0001
Data Index: 635242 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3672. Min Range: -2.3672
Max Act: 2.1062. Min Act: -0.0001
Data Index: 134931 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3672. Min Range: -2.3672
Max Act: 2.1281. Min Act: -0.0001
Data Index: 470230 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3672. Min Range: -2.3672
Max Act: 2.1030. Min Act: -0.0001
Data Index: 1129705 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3672. Min Range: -2.3672
Max Act: 1.9580. Min Act: -0.0001
Data Index: 604221 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3672. Min Range: -2.3672
Max Act: 2.0193. Min Act: -0.0001
Data Index: 960195 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3672. Min Range: -2.3672
Max Act: 2.0089. Min Act: -0.0001
Data Index: 703519 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3672. Min Range: -2.3672
Max Act: 2.0088. Min Act: -0.0001
Data Index: 1113313 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3672. Min Range: -2.3672
Max Act: 1.9920. Min Act: -0.0001
Data Index: 291031 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3672. Min Range: -2.3672
Max Act: 1.9775. Min Act: -0.0001
Data Index: 135450 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3672. Min Range: -2.3672
Max Act: 1.9320. Min Act: -0.0001
Data Index: 1167432 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3672. Min Range: -2.3672
Max Act: 1.9628. Min Act: -0.0001
Data Index: 529368 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3672. Min Range: -2.3672
Max Act: 1.8872. Min Act: -0.0001
Data Index: 1199368 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3672. Min Range: -2.3672
Max Act: 1.7956. Min Act: -0.0001
Data Index: 17945 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3672. Min Range: -2.3672
Max Act: 1.8287. Min Act: -0.0001
Data Index: 152035 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3672. Min Range: -2.3672
Max Act: 1.8850. Min Act: -0.0001
Data Index: 427416 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19