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

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

Neuron 3738 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0645. Min Act: -0.0001

Data Index: 262099 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0267. Min Act: -0.0001

Data Index: 210074 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0265. Min Act: -0.0001

Data Index: 906696 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0316. Min Act: -0.0001

Data Index: 555216 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0272. Min Act: -0.0001

Data Index: 1281043 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0264. Min Act: -0.0001

Data Index: 493625 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0242. Min Act: -0.0001

Data Index: 724310 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0207. Min Act: -0.0001

Data Index: 384128 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0222. Min Act: -0.0001

Data Index: 50424 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0237. Min Act: -0.0001

Data Index: 362568 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0211. Min Act: -0.0001

Data Index: 317063 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0219. Min Act: -0.0001

Data Index: 4238 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0218. Min Act: -0.0001

Data Index: 320566 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0185. Min Act: -0.0001

Data Index: 550124 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0227. Min Act: -0.0001

Data Index: 203799 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0225. Min Act: -0.0001

Data Index: 916367 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0207. Min Act: -0.0001

Data Index: 181044 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0207. Min Act: -0.0001

Data Index: 1194084 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0211. Min Act: -0.0001

Data Index: 440604 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0204. Min Act: -0.0001

Data Index: 1344020 (C4 (Web Text))

Max Activating Token Index: 680