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

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

Neuron 3866 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.4216. Min Act: -0.0000

Data Index: 778934 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.4111. Min Act: -0.0000

Data Index: 605532 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.3833. Min Act: 0.0001

Data Index: 1098268 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1200856 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.3291. Min Act: -0.0000

Data Index: 1278115 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.2906. Min Act: -0.0000

Data Index: 58430 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.3198. Min Act: -0.0000

Data Index: 305626 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.3349. Min Act: -0.0000

Data Index: 705305 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.3061. Min Act: -0.0000

Data Index: 54194 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.3180. Min Act: -0.0000

Data Index: 1035696 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.2900. Min Act: -0.0000

Data Index: 688850 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.3124. Min Act: 0.0001

Data Index: 483421 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.2887. Min Act: -0.0000

Data Index: 758186 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.2703. Min Act: -0.0000

Data Index: 148384 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.2904. Min Act: -0.0000

Data Index: 1220915 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.3182. Min Act: -0.0000

Data Index: 519473 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.3037. Min Act: -0.0000

Data Index: 731425 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.3236. Min Act: -0.0000

Data Index: 175567 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.2880. Min Act: -0.0000

Data Index: 416869 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.4216. Min Range: -0.4216

Max Act: 0.2837. Min Act: -0.0000

Data Index: 956879 (C4 (Web Text))

Max Activating Token Index: 161