Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 237 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0235. Min Act: -0.0006

Data Index: 90417 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0233. Min Act: -0.0006

Data Index: 1478107 (Python Code)

Max Activating Token Index: 483

Text #2

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1572766 (Python Code)

Max Activating Token Index: 168

Text #3

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0228. Min Act: -0.0006

Data Index: 302896 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0223. Min Act: -0.0006

Data Index: 886799 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0218. Min Act: -0.0006

Data Index: 513822 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1563225 (Python Code)

Max Activating Token Index: 133

Text #7

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0225. Min Act: -0.0006

Data Index: 9969 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0211. Min Act: -0.0006

Data Index: 79682 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0214. Min Act: -0.0006

Data Index: 673340 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0208. Min Act: -0.0006

Data Index: 1278678 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0213. Min Act: -0.0006

Data Index: 625592 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1010733 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0206. Min Act: -0.0006

Data Index: 35275 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0215. Min Act: -0.0006

Data Index: 1375609 (Python Code)

Max Activating Token Index: 690

Text #15

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0206. Min Act: -0.0006

Data Index: 228009 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1502146 (Python Code)

Max Activating Token Index: 294

Text #17

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0215. Min Act: -0.0006

Data Index: 686897 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0210. Min Act: -0.0006

Data Index: 238696 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0214. Min Act: -0.0006

Data Index: 869010 (C4 (Web Text))

Max Activating Token Index: 155