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

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

Neuron 1789 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2693. Min Act: -0.0001

Data Index: 1047553 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2657. Min Act: -0.0001

Data Index: 616860 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2211. Min Act: -0.0001

Data Index: 27245 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2372. Min Act: -0.0001

Data Index: 1352771 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2284. Min Act: -0.0001

Data Index: 430538 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2337. Min Act: -0.0001

Data Index: 195165 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2401. Min Act: -0.0001

Data Index: 450778 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2301. Min Act: -0.0001

Data Index: 1165175 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2284. Min Act: -0.0001

Data Index: 894637 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2269. Min Act: -0.0001

Data Index: 601015 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2188. Min Act: -0.0001

Data Index: 498648 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2274. Min Act: -0.0001

Data Index: 482629 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2352. Min Act: -0.0001

Data Index: 867195 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2241. Min Act: -0.0001

Data Index: 287219 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2305. Min Act: -0.0001

Data Index: 1292581 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2216. Min Act: -0.0001

Data Index: 580165 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2199. Min Act: -0.0001

Data Index: 1193198 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2186. Min Act: -0.0001

Data Index: 403990 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2198. Min Act: -0.0001

Data Index: 378078 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.2693. Min Range: -0.2693

Max Act: 0.2190. Min Act: -0.0001

Data Index: 421178 (C4 (Web Text))

Max Activating Token Index: 957