Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5892 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.8239. Min Act: -0.0000

Data Index: 575945 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.5269. Min Act: -0.0000

Data Index: 51332 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.3881. Min Act: -0.0000

Data Index: 721567 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.4357. Min Act: -0.0000

Data Index: 810468 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.3485. Min Act: -0.0000

Data Index: 114827 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.3172. Min Act: -0.0000

Data Index: 519373 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.3105. Min Act: -0.0000

Data Index: 971794 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.2878. Min Act: -0.0000

Data Index: 572460 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.3868. Min Act: -0.0000

Data Index: 1299393 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.1731. Min Act: -0.0000

Data Index: 287276 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.1962. Min Act: -0.0000

Data Index: 1169077 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.1084. Min Act: -0.0000

Data Index: 1215502 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 2.8239. Min Range: -2.8239

Max Act: 1.9860. Min Act: -0.0000

Data Index: 1162759 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.2148. Min Act: -0.0000

Data Index: 163193 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.1798. Min Act: -0.0000

Data Index: 916622 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.2241. Min Act: -0.0000

Data Index: 1296604 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 2.8239. Min Range: -2.8239

Max Act: 1.9847. Min Act: -0.0000

Data Index: 826311 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.0729. Min Act: -0.0000

Data Index: 357104 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 2.8239. Min Range: -2.8239

Max Act: 1.9104. Min Act: -0.0000

Data Index: 917484 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 2.8239. Min Range: -2.8239

Max Act: 1.9098. Min Act: -0.0000

Data Index: 854291 (C4 (Web Text))

Max Activating Token Index: 418