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

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

Neuron 3313 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.9260. Min Act: -0.0001

Data Index: 726832 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.5870. Min Act: -0.0001

Data Index: 634278 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.6300. Min Act: -0.0001

Data Index: 935749 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.6509. Min Act: -0.0001

Data Index: 516282 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.5338. Min Act: -0.0001

Data Index: 1333430 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.4929. Min Act: -0.0001

Data Index: 485625 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.5177. Min Act: -0.0001

Data Index: 748889 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.4925. Min Act: -0.0001

Data Index: 1087371 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.4670. Min Act: -0.0001

Data Index: 387438 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.4672. Min Act: -0.0001

Data Index: 520360 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.3888. Min Act: -0.0001

Data Index: 826822 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.3931. Min Act: -0.0001

Data Index: 1300507 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.3970. Min Act: -0.0001

Data Index: 1086815 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.3869. Min Act: -0.0001

Data Index: 635443 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.4200. Min Act: -0.0001

Data Index: 1085912 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.4216. Min Act: -0.0001

Data Index: 514108 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.2414. Min Act: -0.0001

Data Index: 41053 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.3161. Min Act: -0.0001

Data Index: 457868 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.3806. Min Act: -0.0001

Data Index: 1279243 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 1.9260. Min Range: -1.9260

Max Act: 1.3272. Min Act: -0.0001

Data Index: 594624 (C4 (Web Text))

Max Activating Token Index: 32