Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2164 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 4.9584. Min Range: -4.9584
Max Act: 4.1535. Min Act: -0.0001
Data Index: 16695 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9584. Min Range: -4.9584
Max Act: 4.6535. Min Act: -0.0001
Data Index: 426802 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9584. Min Range: -4.9584
Max Act: 4.9584. Min Act: -0.0001
Data Index: 605165 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9584. Min Range: -4.9584
Max Act: 3.7021. Min Act: -0.0001
Data Index: 1227027 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9584. Min Range: -4.9584
Max Act: 4.3951. Min Act: -0.0001
Data Index: 613692 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9584. Min Range: -4.9584
Max Act: 3.7024. Min Act: -0.0001
Data Index: 1314236 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9584. Min Range: -4.9584
Max Act: 3.8634. Min Act: -0.0001
Data Index: 579726 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9584. Min Range: -4.9584
Max Act: 4.1804. Min Act: -0.0001
Data Index: 555861 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9584. Min Range: -4.9584
Max Act: 4.1435. Min Act: -0.0001
Data Index: 214183 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9584. Min Range: -4.9584
Max Act: 3.8511. Min Act: -0.0001
Data Index: 1645544 (Python Code)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9584. Min Range: -4.9584
Max Act: 3.9746. Min Act: -0.0001
Data Index: 1217056 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9584. Min Range: -4.9584
Max Act: 3.8205. Min Act: -0.0001
Data Index: 489695 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9584. Min Range: -4.9584
Max Act: 3.6517. Min Act: -0.0001
Data Index: 1304179 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9584. Min Range: -4.9584
Max Act: 3.9753. Min Act: -0.0001
Data Index: 1556926 (Python Code)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9584. Min Range: -4.9584
Max Act: 4.0735. Min Act: -0.0001
Data Index: 1307912 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9584. Min Range: -4.9584
Max Act: 3.5912. Min Act: -0.0001
Data Index: 621680 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9584. Min Range: -4.9584
Max Act: 3.8992. Min Act: -0.0001
Data Index: 754748 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9584. Min Range: -4.9584
Max Act: 3.9171. Min Act: -0.0001
Data Index: 1610859 (Python Code)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9584. Min Range: -4.9584
Max Act: 4.0211. Min Act: -0.0001
Data Index: 1145993 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9584. Min Range: -4.9584
Max Act: 4.0522. Min Act: -0.0001
Data Index: 1500208 (Python Code)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19