Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4067 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.6047. Min Range: -3.6047

Max Act: 3.6047. Min Act: -0.0001

Data Index: 739327 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 3.6047. Min Range: -3.6047

Max Act: 3.4585. Min Act: -0.0001

Data Index: 1129733 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 3.6047. Min Range: -3.6047

Max Act: 3.4344. Min Act: -0.0001

Data Index: 153044 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 3.6047. Min Range: -3.6047

Max Act: 3.0119. Min Act: -0.0001

Data Index: 1630312 (Python Code)

Max Activating Token Index: 969

Text #4

Max Range: 3.6047. Min Range: -3.6047

Max Act: 3.4223. Min Act: -0.0001

Data Index: 468540 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 3.6047. Min Range: -3.6047

Max Act: 3.1283. Min Act: -0.0001

Data Index: 1446236 (Python Code)

Max Activating Token Index: 368

Text #6

Max Range: 3.6047. Min Range: -3.6047

Max Act: 3.0841. Min Act: -0.0001

Data Index: 1427286 (Python Code)

Max Activating Token Index: 241

Text #7

Max Range: 3.6047. Min Range: -3.6047

Max Act: 2.9151. Min Act: -0.0001

Data Index: 650441 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 3.6047. Min Range: -3.6047

Max Act: 2.9270. Min Act: -0.0001

Data Index: 1518541 (Python Code)

Max Activating Token Index: 934

Text #9

Max Range: 3.6047. Min Range: -3.6047

Max Act: 3.0642. Min Act: -0.0001

Data Index: 653106 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 3.6047. Min Range: -3.6047

Max Act: 2.9186. Min Act: -0.0001

Data Index: 811535 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 3.6047. Min Range: -3.6047

Max Act: 2.9029. Min Act: -0.0001

Data Index: 890187 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 3.6047. Min Range: -3.6047

Max Act: 3.2925. Min Act: -0.0001

Data Index: 223805 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 3.6047. Min Range: -3.6047

Max Act: 3.1176. Min Act: -0.0001

Data Index: 949153 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 3.6047. Min Range: -3.6047

Max Act: 2.7891. Min Act: -0.0001

Data Index: 1449943 (Python Code)

Max Activating Token Index: 980

Text #15

Max Range: 3.6047. Min Range: -3.6047

Max Act: 2.9413. Min Act: -0.0001

Data Index: 989622 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 3.6047. Min Range: -3.6047

Max Act: 2.9818. Min Act: -0.0001

Data Index: 1571126 (Python Code)

Max Activating Token Index: 924

Text #17

Max Range: 3.6047. Min Range: -3.6047

Max Act: 3.1506. Min Act: -0.0001

Data Index: 1384829 (Python Code)

Max Activating Token Index: 1007

Text #18

Max Range: 3.6047. Min Range: -3.6047

Max Act: 2.7202. Min Act: -0.0001

Data Index: 1620431 (Python Code)

Max Activating Token Index: 981

Text #19

Max Range: 3.6047. Min Range: -3.6047

Max Act: 2.6917. Min Act: -0.0001

Data Index: 221633 (C4 (Web Text))

Max Activating Token Index: 276