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

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

Neuron 4446 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6259. Min Range: -2.6259

Max Act: 2.6259. Min Act: -0.0000

Data Index: 901111 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 2.6259. Min Range: -2.6259

Max Act: 2.5830. Min Act: -0.0000

Data Index: 30689 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 2.6259. Min Range: -2.6259

Max Act: 2.4654. Min Act: -0.0000

Data Index: 1297555 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 2.6259. Min Range: -2.6259

Max Act: 2.2185. Min Act: -0.0000

Data Index: 1040214 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 2.6259. Min Range: -2.6259

Max Act: 2.2167. Min Act: -0.0000

Data Index: 1331937 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 2.6259. Min Range: -2.6259

Max Act: 2.1651. Min Act: -0.0000

Data Index: 1277391 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 2.6259. Min Range: -2.6259

Max Act: 2.0292. Min Act: -0.0000

Data Index: 821577 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 2.6259. Min Range: -2.6259

Max Act: 2.2339. Min Act: -0.0000

Data Index: 137798 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 2.6259. Min Range: -2.6259

Max Act: 2.0012. Min Act: -0.0000

Data Index: 1311318 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 2.6259. Min Range: -2.6259

Max Act: 2.0917. Min Act: -0.0000

Data Index: 132122 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 2.6259. Min Range: -2.6259

Max Act: 2.0272. Min Act: -0.0000

Data Index: 298812 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 2.6259. Min Range: -2.6259

Max Act: 1.9043. Min Act: -0.0000

Data Index: 850645 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 2.6259. Min Range: -2.6259

Max Act: 2.1203. Min Act: -0.0000

Data Index: 667777 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 2.6259. Min Range: -2.6259

Max Act: 1.9753. Min Act: -0.0000

Data Index: 712941 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 2.6259. Min Range: -2.6259

Max Act: 1.9833. Min Act: -0.0000

Data Index: 1164357 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 2.6259. Min Range: -2.6259

Max Act: 2.0580. Min Act: -0.0000

Data Index: 135560 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 2.6259. Min Range: -2.6259

Max Act: 1.9534. Min Act: -0.0000

Data Index: 542209 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 2.6259. Min Range: -2.6259

Max Act: 1.9498. Min Act: -0.0000

Data Index: 1188460 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 2.6259. Min Range: -2.6259

Max Act: 2.0546. Min Act: -0.0000

Data Index: 160148 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 2.6259. Min Range: -2.6259

Max Act: 1.9466. Min Act: -0.0000

Data Index: 119383 (C4 (Web Text))

Max Activating Token Index: 297