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

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

Neuron 625 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: 0.0258. Min Range: -0.0258

Max Act: 0.0258. Min Act: -0.0006

Data Index: 4000 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0252. Min Act: -0.0006

Data Index: 1169937 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0239. Min Act: -0.0006

Data Index: 269121 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0238. Min Act: -0.0006

Data Index: 425273 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0220. Min Act: -0.0006

Data Index: 31484 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0227. Min Act: -0.0006

Data Index: 505892 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1069220 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0213. Min Act: -0.0006

Data Index: 468188 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0228. Min Act: -0.0006

Data Index: 580745 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0213. Min Act: -0.0006

Data Index: 177309 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0215. Min Act: -0.0007

Data Index: 903682 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0212. Min Act: -0.0006

Data Index: 198316 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0217. Min Act: -0.0006

Data Index: 655500 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0221. Min Act: -0.0006

Data Index: 493747 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1087871 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0220. Min Act: -0.0006

Data Index: 553939 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1347629 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1389 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0217. Min Act: -0.0006

Data Index: 152984 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0216. Min Act: -0.0006

Data Index: 601075 (C4 (Web Text))

Max Activating Token Index: 479