Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2586 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.5220. Min Act: -0.0001

Data Index: 1146628 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4897. Min Act: -0.0001

Data Index: 830983 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4572. Min Act: -0.0001

Data Index: 925776 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4358. Min Act: -0.0001

Data Index: 827195 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4596. Min Act: -0.0000

Data Index: 917372 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4280. Min Act: -0.0001

Data Index: 1045474 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4527. Min Act: -0.0001

Data Index: 185701 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4173. Min Act: -0.0001

Data Index: 904516 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4314. Min Act: -0.0001

Data Index: 1150131 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4126. Min Act: -0.0001

Data Index: 791186 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3984. Min Act: -0.0001

Data Index: 1031571 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3940. Min Act: -0.0001

Data Index: 738566 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3752. Min Act: -0.0001

Data Index: 576288 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4183. Min Act: -0.0001

Data Index: 1265519 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4163. Min Act: -0.0001

Data Index: 1271893 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4158. Min Act: -0.0001

Data Index: 546954 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3986. Min Act: -0.0001

Data Index: 372079 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3956. Min Act: -0.0001

Data Index: 521660 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.4098. Min Act: -0.0001

Data Index: 933046 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3928. Min Act: -0.0001

Data Index: 223619 (C4 (Web Text))

Max Activating Token Index: 648