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

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

Neuron 5197 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.2172. Min Act: -0.0000

Data Index: 1162336 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.1647. Min Act: -0.0000

Data Index: 822394 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.0011. Min Act: -0.0000

Data Index: 377926 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 1.2172. Min Range: -1.2172

Max Act: 0.9983. Min Act: -0.0000

Data Index: 376010 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 1.2172. Min Range: -1.2172

Max Act: 0.9938. Min Act: -0.0000

Data Index: 604244 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.0105. Min Act: -0.0000

Data Index: 815437 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 1.2172. Min Range: -1.2172

Max Act: 1.0038. Min Act: -0.0000

Data Index: 435544 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 1.2172. Min Range: -1.2172

Max Act: 0.9765. Min Act: -0.0000

Data Index: 838181 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 1.2172. Min Range: -1.2172

Max Act: 0.9179. Min Act: -0.0000

Data Index: 13169 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 1.2172. Min Range: -1.2172

Max Act: 0.8421. Min Act: -0.0000

Data Index: 578602 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 1.2172. Min Range: -1.2172

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1272437 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 1.2172. Min Range: -1.2172

Max Act: 0.8907. Min Act: -0.0000

Data Index: 854457 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 1.2172. Min Range: -1.2172

Max Act: 0.8714. Min Act: -0.0000

Data Index: 350939 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 1.2172. Min Range: -1.2172

Max Act: 0.8609. Min Act: -0.0000

Data Index: 378977 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 1.2172. Min Range: -1.2172

Max Act: 0.8543. Min Act: -0.0000

Data Index: 208120 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 1.2172. Min Range: -1.2172

Max Act: 0.8864. Min Act: -0.0000

Data Index: 65282 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 1.2172. Min Range: -1.2172

Max Act: 0.8266. Min Act: -0.0000

Data Index: 875277 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 1.2172. Min Range: -1.2172

Max Act: 0.9112. Min Act: -0.0000

Data Index: 154786 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 1.2172. Min Range: -1.2172

Max Act: 0.8291. Min Act: -0.0000

Data Index: 209266 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 1.2172. Min Range: -1.2172

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1030406 (C4 (Web Text))

Max Activating Token Index: 524