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

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

Neuron 2950 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.3205. Min Act: -0.0001

Data Index: 1309789 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.3012. Min Act: -0.0000

Data Index: 563726 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2973. Min Act: -0.0001

Data Index: 550010 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2773. Min Act: -0.0000

Data Index: 905946 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2798. Min Act: -0.0001

Data Index: 692583 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2693. Min Act: -0.0000

Data Index: 6927 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2452. Min Act: -0.0001

Data Index: 738966 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2224. Min Act: -0.0001

Data Index: 422118 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2344. Min Act: -0.0000

Data Index: 984627 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2366. Min Act: -0.0000

Data Index: 847651 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2270. Min Act: -0.0000

Data Index: 980270 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2169. Min Act: -0.0001

Data Index: 434519 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2155. Min Act: -0.0001

Data Index: 1099335 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1283319 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2206. Min Act: -0.0001

Data Index: 1282486 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2292. Min Act: -0.0001

Data Index: 1092816 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2130. Min Act: -0.0000

Data Index: 261149 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.1966. Min Act: -0.0000

Data Index: 931447 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2201. Min Act: -0.0001

Data Index: 1132580 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2046. Min Act: -0.0001

Data Index: 535118 (C4 (Web Text))

Max Activating Token Index: 257