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

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

Neuron 2012 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: 0.0305. Min Range: -0.0305

Max Act: 0.0305. Min Act: -0.0006

Data Index: 642506 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0255. Min Act: -0.0006

Data Index: 758562 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0260. Min Act: -0.0006

Data Index: 915607 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0242. Min Act: -0.0006

Data Index: 120687 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0252. Min Act: -0.0006

Data Index: 123521 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0246. Min Act: -0.0006

Data Index: 141350 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0242. Min Act: -0.0006

Data Index: 1281036 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0236. Min Act: -0.0006

Data Index: 650402 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1055548 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1147797 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0229. Min Act: -0.0006

Data Index: 410505 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0221. Min Act: -0.0006

Data Index: 403395 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0215. Min Act: -0.0006

Data Index: 240748 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0225. Min Act: -0.0006

Data Index: 1079114 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0217. Min Act: -0.0006

Data Index: 744996 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0223. Min Act: -0.0006

Data Index: 158611 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0217. Min Act: -0.0006

Data Index: 625511 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0210. Min Act: -0.0006

Data Index: 912090 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0225. Min Act: -0.0006

Data Index: 959887 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0214. Min Act: -0.0006

Data Index: 984742 (C4 (Web Text))

Max Activating Token Index: 600