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

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

Neuron 233 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7358. Min Act: -0.0001

Data Index: 1319441 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7956. Min Act: -0.0001

Data Index: 20194 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7606. Min Act: -0.0001

Data Index: 445234 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7236. Min Act: -0.0001

Data Index: 938480 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7255. Min Act: -0.0001

Data Index: 1201610 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7409. Min Act: -0.0001

Data Index: 550974 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7148. Min Act: -0.0001

Data Index: 37324 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7048. Min Act: -0.0001

Data Index: 225731 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6738. Min Act: -0.0001

Data Index: 1195249 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7176. Min Act: -0.0001

Data Index: 626045 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7202. Min Act: -0.0001

Data Index: 1247875 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7147. Min Act: -0.0001

Data Index: 416986 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6703. Min Act: -0.0001

Data Index: 1313849 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6868. Min Act: -0.0001

Data Index: 315322 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6644. Min Act: -0.0001

Data Index: 895571 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6818. Min Act: -0.0001

Data Index: 52750 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6355. Min Act: -0.0001

Data Index: 920003 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6998. Min Act: -0.0001

Data Index: 251872 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.7183. Min Act: -0.0001

Data Index: 923906 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.7956. Min Range: -0.7956

Max Act: 0.6990. Min Act: -0.0001

Data Index: 109727 (C4 (Web Text))

Max Activating Token Index: 348