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

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

Neuron 2817 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0305. Min Act: -0.0003

Data Index: 791142 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0286. Min Act: -0.0003

Data Index: 67083 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1068541 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1162162 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0255. Min Act: -0.0003

Data Index: 423611 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1101758 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0260. Min Act: -0.0003

Data Index: 328470 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0249. Min Act: -0.0003

Data Index: 847599 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0252. Min Act: -0.0003

Data Index: 642255 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0241. Min Act: -0.0003

Data Index: 575016 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0246. Min Act: -0.0003

Data Index: 407777 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0246. Min Act: -0.0003

Data Index: 991137 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1371690 (Python Code)

Max Activating Token Index: 202

Text #13

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0238. Min Act: -0.0002

Data Index: 1577860 (Python Code)

Max Activating Token Index: 399

Text #14

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0244. Min Act: -0.0003

Data Index: 591068 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0232. Min Act: -0.0003

Data Index: 380540 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0235. Min Act: -0.0003

Data Index: 856784 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1171827 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0238. Min Act: -0.0003

Data Index: 914146 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1170488 (C4 (Web Text))

Max Activating Token Index: 133