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

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

Neuron 819 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2297. Min Act: -0.0000

Data Index: 741992 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1717. Min Act: -0.0000

Data Index: 129671 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1576. Min Act: -0.0000

Data Index: 97535 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1463. Min Act: -0.0000

Data Index: 564106 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1289. Min Act: -0.0000

Data Index: 825118 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1299. Min Act: -0.0000

Data Index: 10105 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1345. Min Act: -0.0000

Data Index: 480386 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1292. Min Act: -0.0000

Data Index: 112781 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1286. Min Act: -0.0000

Data Index: 830691 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1216. Min Act: -0.0000

Data Index: 1304699 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1213. Min Act: -0.0000

Data Index: 85019 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1240. Min Act: -0.0000

Data Index: 91478 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1287. Min Act: -0.0000

Data Index: 156018 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1294. Min Act: -0.0000

Data Index: 202306 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1280. Min Act: -0.0000

Data Index: 32658 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1228. Min Act: -0.0000

Data Index: 946059 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1127031 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1237. Min Act: -0.0000

Data Index: 770027 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1130. Min Act: -0.0000

Data Index: 123125 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1175. Min Act: -0.0000

Data Index: 686460 (C4 (Web Text))

Max Activating Token Index: 806