Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2987 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1028294 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1293598 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3705. Min Act: -0.0001

Data Index: 277249 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1303288 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3551. Min Act: -0.0000

Data Index: 93427 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3496. Min Act: -0.0000

Data Index: 562465 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1277017 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3352. Min Act: -0.0000

Data Index: 193193 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1182690 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3262. Min Act: -0.0000

Data Index: 15078 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3337. Min Act: -0.0000

Data Index: 942478 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3225. Min Act: -0.0000

Data Index: 262557 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3356. Min Act: -0.0001

Data Index: 738267 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3247. Min Act: -0.0000

Data Index: 886210 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3207. Min Act: -0.0000

Data Index: 968315 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3073. Min Act: -0.0001

Data Index: 45107 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3195. Min Act: -0.0001

Data Index: 411171 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3048. Min Act: -0.0001

Data Index: 759584 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3200. Min Act: -0.0000

Data Index: 927610 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.5325. Min Range: -0.5325

Max Act: 0.3138. Min Act: -0.0000

Data Index: 621545 (C4 (Web Text))

Max Activating Token Index: 143