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

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

Neuron 5567 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2670. Min Act: -0.0000

Data Index: 180090 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2559. Min Act: -0.0000

Data Index: 191530 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1252710 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2362. Min Act: -0.0000

Data Index: 891017 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2292. Min Act: -0.0000

Data Index: 1032137 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2286. Min Act: -0.0000

Data Index: 136208 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2268. Min Act: -0.0000

Data Index: 25276 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2181. Min Act: -0.0000

Data Index: 867872 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2141. Min Act: -0.0000

Data Index: 786831 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2184. Min Act: -0.0000

Data Index: 88617 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2111. Min Act: -0.0000

Data Index: 455418 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2040. Min Act: -0.0000

Data Index: 858894 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2001. Min Act: -0.0000

Data Index: 341341 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2111. Min Act: -0.0000

Data Index: 1075297 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1098862 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2091. Min Act: -0.0000

Data Index: 654552 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1993. Min Act: -0.0000

Data Index: 262482 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1989. Min Act: -0.0000

Data Index: 51504 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1916. Min Act: -0.0000

Data Index: 800172 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1171543 (C4 (Web Text))

Max Activating Token Index: 151