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

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

Neuron 2345 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.4044. Min Act: -0.0001

Data Index: 1205163 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.4250. Min Act: -0.0001

Data Index: 769204 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3723. Min Act: -0.0001

Data Index: 1202205 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3842. Min Act: -0.0001

Data Index: 1183747 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3411. Min Act: -0.0001

Data Index: 1155130 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3106. Min Act: -0.0001

Data Index: 819840 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3204. Min Act: -0.0001

Data Index: 252899 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3223. Min Act: -0.0001

Data Index: 674802 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3279. Min Act: -0.0001

Data Index: 754559 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3031. Min Act: -0.0001

Data Index: 1143421 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3154. Min Act: -0.0001

Data Index: 500063 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3196. Min Act: -0.0001

Data Index: 166311 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3226. Min Act: -0.0001

Data Index: 951712 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3457. Min Act: -0.0001

Data Index: 714446 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3278. Min Act: -0.0001

Data Index: 272604 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3028. Min Act: -0.0001

Data Index: 1145098 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3042. Min Act: -0.0001

Data Index: 104875 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3117. Min Act: -0.0001

Data Index: 706542 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3206. Min Act: -0.0001

Data Index: 1295321 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3486. Min Act: -0.0001

Data Index: 1322831 (C4 (Web Text))

Max Activating Token Index: 133