Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2539 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.5248. Min Act: -0.0000

Data Index: 843198 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4859. Min Act: -0.0000

Data Index: 425527 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4594. Min Act: -0.0000

Data Index: 789710 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4540. Min Act: -0.0000

Data Index: 664157 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4436. Min Act: -0.0000

Data Index: 51504 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4375. Min Act: -0.0000

Data Index: 1027227 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4344. Min Act: -0.0000

Data Index: 669247 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4468. Min Act: -0.0000

Data Index: 882842 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4254. Min Act: -0.0000

Data Index: 365091 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4185. Min Act: -0.0000

Data Index: 809026 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4151. Min Act: -0.0000

Data Index: 763701 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4160. Min Act: -0.0000

Data Index: 91782 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1086370 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4017. Min Act: -0.0000

Data Index: 1058270 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4001. Min Act: -0.0000

Data Index: 1020601 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1215110 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4095. Min Act: -0.0000

Data Index: 886110 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3951. Min Act: -0.0000

Data Index: 891599 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.4025. Min Act: -0.0000

Data Index: 177548 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.5248. Min Range: -0.5248

Max Act: 0.3857. Min Act: -0.0000

Data Index: 1002471 (C4 (Web Text))

Max Activating Token Index: 938