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

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

Neuron 3549 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.5176. Min Act: -0.0001

Data Index: 928050 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4481. Min Act: -0.0001

Data Index: 426824 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4566. Min Act: -0.0001

Data Index: 364822 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4177. Min Act: -0.0000

Data Index: 125094 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4130. Min Act: -0.0001

Data Index: 1277894 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4295. Min Act: -0.0001

Data Index: 1167089 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4027. Min Act: -0.0001

Data Index: 54474 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3937. Min Act: -0.0001

Data Index: 774977 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4160. Min Act: -0.0001

Data Index: 498873 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4015. Min Act: -0.0000

Data Index: 1279147 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3796. Min Act: -0.0001

Data Index: 845219 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3912. Min Act: -0.0001

Data Index: 280161 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3786. Min Act: -0.0000

Data Index: 15487 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3905. Min Act: -0.0001

Data Index: 1191750 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3833. Min Act: -0.0001

Data Index: 612325 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3686. Min Act: -0.0001

Data Index: 683320 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3513. Min Act: -0.0000

Data Index: 91398 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3482. Min Act: -0.0001

Data Index: 741246 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1478889 (Python Code)

Max Activating Token Index: 85

Text #19

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3513. Min Act: -0.0001

Data Index: 498957 (C4 (Web Text))

Max Activating Token Index: 801