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

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

Neuron 2117 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0342. Min Act: -0.0004

Data Index: 1133327 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0302. Min Act: -0.0004

Data Index: 610755 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0366. Min Act: -0.0004

Data Index: 299765 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0293. Min Act: -0.0004

Data Index: 755125 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0314. Min Act: -0.0004

Data Index: 580125 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0249. Min Act: -0.0004

Data Index: 316295 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0312. Min Act: -0.0004

Data Index: 846828 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0287. Min Act: -0.0004

Data Index: 52705 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0243. Min Act: -0.0004

Data Index: 125164 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0298. Min Act: -0.0004

Data Index: 370343 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0247. Min Act: -0.0004

Data Index: 779513 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0282. Min Act: -0.0004

Data Index: 591561 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0237. Min Act: -0.0004

Data Index: 213212 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0287. Min Act: -0.0004

Data Index: 930812 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0281. Min Act: -0.0004

Data Index: 233928 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0305. Min Act: -0.0004

Data Index: 1149185 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0268. Min Act: -0.0004

Data Index: 195224 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0274. Min Act: -0.0004

Data Index: 967177 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0236. Min Act: -0.0004

Data Index: 293646 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0235. Min Act: -0.0004

Data Index: 715046 (C4 (Web Text))

Max Activating Token Index: 655