Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2496 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0512. Min Act: -0.0001

Data Index: 59359 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0253. Min Act: -0.0001

Data Index: 1556648 (Python Code)

Max Activating Token Index: 158

Text #2

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0247. Min Act: -0.0001

Data Index: 1420835 (Python Code)

Max Activating Token Index: 83

Text #3

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0235. Min Act: -0.0002

Data Index: 358108 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0228. Min Act: -0.0002

Data Index: 788239 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0266. Min Act: -0.0001

Data Index: 1519467 (Python Code)

Max Activating Token Index: 146

Text #6

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0240. Min Act: -0.0001

Data Index: 1547976 (Python Code)

Max Activating Token Index: 511

Text #7

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0234. Min Act: -0.0001

Data Index: 1426977 (Python Code)

Max Activating Token Index: 249

Text #8

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0237. Min Act: -0.0001

Data Index: 628731 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0223. Min Act: -0.0001

Data Index: 48792 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0220. Min Act: -0.0001

Data Index: 1578532 (Python Code)

Max Activating Token Index: 470

Text #11

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0239. Min Act: -0.0001

Data Index: 1640702 (Python Code)

Max Activating Token Index: 834

Text #12

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0218. Min Act: -0.0001

Data Index: 1511279 (Python Code)

Max Activating Token Index: 288

Text #13

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0215. Min Act: -0.0001

Data Index: 1536628 (Python Code)

Max Activating Token Index: 86

Text #14

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1640191 (Python Code)

Max Activating Token Index: 116

Text #15

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0211. Min Act: -0.0001

Data Index: 1494243 (Python Code)

Max Activating Token Index: 142

Text #16

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0210. Min Act: -0.0001

Data Index: 1493227 (Python Code)

Max Activating Token Index: 563

Text #17

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0221. Min Act: -0.0001

Data Index: 1519266 (Python Code)

Max Activating Token Index: 304

Text #18

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0199. Min Act: -0.0001

Data Index: 1486418 (Python Code)

Max Activating Token Index: 535

Text #19

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0204. Min Act: -0.0002

Data Index: 91806 (C4 (Web Text))

Max Activating Token Index: 876