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

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

Neuron 5969 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0222. Min Act: -0.0001

Data Index: 1140913 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0217. Min Act: -0.0001

Data Index: 620720 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0216. Min Act: -0.0001

Data Index: 26493 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0218. Min Act: -0.0001

Data Index: 1150938 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0218. Min Act: -0.0001

Data Index: 33155 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0217. Min Act: -0.0001

Data Index: 1496878 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0213. Min Act: -0.0001

Data Index: 1019503 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0211. Min Act: -0.0001

Data Index: 329467 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0210. Min Act: -0.0001

Data Index: 453461 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0210. Min Act: -0.0001

Data Index: 1451216 (Python Code)

Max Activating Token Index: 27

Text #10

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0210. Min Act: -0.0001

Data Index: 677899 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0210. Min Act: -0.0001

Data Index: 486655 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0207. Min Act: -0.0001

Data Index: 1039911 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0206. Min Act: -0.0001

Data Index: 1600364 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0205. Min Act: -0.0001

Data Index: 453939 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0204. Min Act: -0.0001

Data Index: 486185 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0204. Min Act: -0.0001

Data Index: 1130243 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0206. Min Act: -0.0001

Data Index: 1023355 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1175426 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0208. Min Act: -0.0001

Data Index: 1023077 (C4 (Web Text))

Max Activating Token Index: 208