Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 427 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0235. Min Act: -0.0006

Data Index: 626603 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0246. Min Act: -0.0006

Data Index: 476781 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0252. Min Act: -0.0006

Data Index: 1100095 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0217. Min Act: -0.0006

Data Index: 259565 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1133770 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0228. Min Act: -0.0006

Data Index: 71766 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0233. Min Act: -0.0006

Data Index: 608339 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0234. Min Act: -0.0006

Data Index: 29059 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0228. Min Act: -0.0006

Data Index: 1874 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0232. Min Act: -0.0006

Data Index: 1152909 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0202. Min Act: -0.0006

Data Index: 1062088 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0250. Min Act: -0.0006

Data Index: 532688 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0225. Min Act: -0.0006

Data Index: 982978 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0231. Min Act: -0.0006

Data Index: 131953 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0230. Min Act: -0.0006

Data Index: 525058 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0219. Min Act: -0.0006

Data Index: 1005897 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0230. Min Act: -0.0006

Data Index: 159814 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0228. Min Act: -0.0006

Data Index: 159219 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0223. Min Act: -0.0006

Data Index: 914012 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0231. Min Act: -0.0006

Data Index: 421181 (C4 (Web Text))

Max Activating Token Index: 83