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

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

Neuron 2724 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.3118. Min Act: 0.0001

Data Index: 1149806 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1333629 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2878. Min Act: -0.0000

Data Index: 323358 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2656. Min Act: -0.0000

Data Index: 237691 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2640. Min Act: -0.0000

Data Index: 675124 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2539. Min Act: -0.0000

Data Index: 321358 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2796. Min Act: -0.0000

Data Index: 186023 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2299. Min Act: -0.0000

Data Index: 922270 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2440. Min Act: -0.0000

Data Index: 380056 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1238252 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2330. Min Act: -0.0000

Data Index: 566017 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2311. Min Act: -0.0000

Data Index: 1221374 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2202. Min Act: 0.0000

Data Index: 356154 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2268. Min Act: -0.0000

Data Index: 216921 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2326. Min Act: -0.0000

Data Index: 12162 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2159. Min Act: -0.0000

Data Index: 605188 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2266. Min Act: 0.0002

Data Index: 613799 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1151299 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2218. Min Act: 0.0000

Data Index: 917845 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2139. Min Act: -0.0000

Data Index: 240448 (C4 (Web Text))

Max Activating Token Index: 777