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

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

Neuron 3238 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.8194. Min Act: -0.0001

Data Index: 1323763 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.8077. Min Act: -0.0001

Data Index: 1131062 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.7754. Min Act: -0.0001

Data Index: 891486 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.7972. Min Act: -0.0001

Data Index: 475701 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.7441. Min Act: -0.0001

Data Index: 203803 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.7547. Min Act: -0.0001

Data Index: 237886 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.7757. Min Act: -0.0001

Data Index: 866968 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.7243. Min Act: -0.0001

Data Index: 828013 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.7459. Min Act: -0.0001

Data Index: 835048 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.7232. Min Act: -0.0001

Data Index: 1005883 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.7595. Min Act: -0.0001

Data Index: 23096 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.7434. Min Act: -0.0001

Data Index: 250238 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.7139. Min Act: -0.0001

Data Index: 624785 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.7353. Min Act: -0.0001

Data Index: 404776 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.6379. Min Act: -0.0001

Data Index: 929252 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.7119. Min Act: -0.0001

Data Index: 488485 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.7795. Min Act: -0.0001

Data Index: 864188 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.7542. Min Act: -0.0001

Data Index: 357298 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.7246. Min Act: -0.0001

Data Index: 661234 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.8194. Min Range: -0.8194

Max Act: 0.7026. Min Act: -0.0001

Data Index: 804423 (C4 (Web Text))

Max Activating Token Index: 27