Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4202 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.8400. Min Act: -0.0001

Data Index: 285304 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4445. Min Act: -0.0001

Data Index: 191422 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4572. Min Act: -0.0001

Data Index: 870475 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4712. Min Act: -0.0001

Data Index: 4839 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4350. Min Act: -0.0001

Data Index: 1152764 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4633. Min Act: -0.0001

Data Index: 660599 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4369. Min Act: -0.0001

Data Index: 601245 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4324. Min Act: -0.0001

Data Index: 1036285 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4159. Min Act: -0.0001

Data Index: 356504 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4511. Min Act: -0.0001

Data Index: 388248 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4187. Min Act: -0.0001

Data Index: 1279100 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4185. Min Act: -0.0001

Data Index: 981468 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4073. Min Act: -0.0001

Data Index: 1443815 (Python Code)

Max Activating Token Index: 786

Text #13

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4259. Min Act: -0.0001

Data Index: 1114833 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4229. Min Act: -0.0001

Data Index: 759257 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4267. Min Act: -0.0001

Data Index: 1356341 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.3999. Min Act: -0.0001

Data Index: 740251 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4117. Min Act: -0.0001

Data Index: 1015021 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4072. Min Act: -0.0001

Data Index: 1155076 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.4314. Min Act: -0.0001

Data Index: 790497 (C4 (Web Text))

Max Activating Token Index: 301