Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3976 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0332. Min Act: -0.0000

Data Index: 514256 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0333. Min Act: -0.0000

Data Index: 74084 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0312. Min Act: -0.0000

Data Index: 843142 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0269. Min Act: -0.0000

Data Index: 723681 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0244. Min Act: -0.0000

Data Index: 1417738 (Python Code)

Max Activating Token Index: 16

Text #5

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0256. Min Act: -0.0000

Data Index: 1272902 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0266. Min Act: -0.0000

Data Index: 779444 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0247. Min Act: -0.0000

Data Index: 916143 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0231. Min Act: -0.0000

Data Index: 1149515 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0247. Min Act: -0.0000

Data Index: 378244 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0227. Min Act: -0.0000

Data Index: 867554 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0242. Min Act: -0.0000

Data Index: 844947 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0244. Min Act: -0.0000

Data Index: 1343801 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0234. Min Act: -0.0000

Data Index: 707024 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0225. Min Act: -0.0001

Data Index: 541755 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0231. Min Act: -0.0000

Data Index: 993135 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0241. Min Act: -0.0000

Data Index: 1069025 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0231. Min Act: -0.0000

Data Index: 806430 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0236. Min Act: -0.0000

Data Index: 684943 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0235. Min Act: -0.0000

Data Index: 982279 (C4 (Web Text))

Max Activating Token Index: 391