Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 561 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.5443. Min Act: -0.0003

Data Index: 75624 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.4802. Min Act: -0.0003

Data Index: 1114863 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.4224. Min Act: -0.0003

Data Index: 882380 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.1266. Min Act: -0.0003

Data Index: 179606 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.4916. Min Act: -0.0003

Data Index: 1151518 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.1905. Min Act: -0.0003

Data Index: 1119036 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.2124. Min Act: -0.0003

Data Index: 1136189 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.2045. Min Act: -0.0003

Data Index: 936695 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.2019. Min Act: -0.0003

Data Index: 346346 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.1467. Min Act: -0.0003

Data Index: 942902 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.1629. Min Act: -0.0003

Data Index: 810474 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.0819. Min Act: -0.0003

Data Index: 451895 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.0945. Min Act: -0.0003

Data Index: 1245566 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.0286. Min Act: -0.0003

Data Index: 999842 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.0159. Min Act: -0.0003

Data Index: 27473 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 1.5443. Min Range: -1.5443

Max Act: 0.9786. Min Act: -0.0003

Data Index: 51957 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.0656. Min Act: -0.0003

Data Index: 913821 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.0257. Min Act: -0.0003

Data Index: 1080711 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.0874. Min Act: -0.0003

Data Index: 176544 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.0176. Min Act: -0.0003

Data Index: 735780 (C4 (Web Text))

Max Activating Token Index: 971