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

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

Neuron 4152 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0245. Min Act: -0.0002

Data Index: 672513 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0297. Min Act: -0.0002

Data Index: 415928 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0002

Data Index: 71464 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0260. Min Act: -0.0002

Data Index: 759921 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1116888 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0227. Min Act: -0.0002

Data Index: 342396 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0293. Min Act: -0.0002

Data Index: 695065 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1088107 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0240. Min Act: -0.0002

Data Index: 491103 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0278. Min Act: -0.0002

Data Index: 1229381 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0239. Min Act: -0.0002

Data Index: 987616 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0258. Min Act: -0.0002

Data Index: 1197012 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1060038 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0249. Min Act: -0.0002

Data Index: 34420 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0241. Min Act: -0.0002

Data Index: 756083 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0224. Min Act: -0.0002

Data Index: 955291 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0224. Min Act: -0.0002

Data Index: 742325 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1232993 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0195. Min Act: -0.0002

Data Index: 417114 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1282127 (C4 (Web Text))

Max Activating Token Index: 778