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

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

Neuron 2997 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.4109. Min Act: -0.0001

Data Index: 955716 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.5611. Min Act: -0.0001

Data Index: 1197449 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.3936. Min Act: -0.0001

Data Index: 219402 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.4280. Min Act: -0.0001

Data Index: 646227 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.3279. Min Act: -0.0001

Data Index: 1094997 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.4045. Min Act: -0.0001

Data Index: 1239767 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.4297. Min Act: -0.0001

Data Index: 347093 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.5478. Min Act: -0.0001

Data Index: 394166 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.3358. Min Act: -0.0001

Data Index: 290087 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.3196. Min Act: -0.0001

Data Index: 756395 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.3608. Min Act: -0.0001

Data Index: 294840 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.3336. Min Act: -0.0001

Data Index: 41526 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.4179. Min Act: -0.0001

Data Index: 620025 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.2936. Min Act: -0.0001

Data Index: 437190 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.3020. Min Act: -0.0001

Data Index: 213050 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.4799. Min Act: -0.0001

Data Index: 1080710 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.3644. Min Act: -0.0001

Data Index: 411900 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.4056. Min Act: -0.0001

Data Index: 326259 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.1349. Min Act: -0.0001

Data Index: 1028947 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 1.5611. Min Range: -1.5611

Max Act: 1.2802. Min Act: -0.0001

Data Index: 1261320 (C4 (Web Text))

Max Activating Token Index: 4