Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 870 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1792. Min Act: -0.0003

Data Index: 1149105 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1490. Min Act: -0.0003

Data Index: 1278688 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1495. Min Act: -0.0003

Data Index: 1023214 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1479. Min Act: -0.0003

Data Index: 913268 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1433. Min Act: -0.0003

Data Index: 36548 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1433. Min Act: -0.0003

Data Index: 372642 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1422. Min Act: -0.0003

Data Index: 1352438 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1249. Min Act: -0.0003

Data Index: 1073582 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1311. Min Act: -0.0003

Data Index: 927815 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1274. Min Act: -0.0003

Data Index: 768967 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1219. Min Act: -0.0003

Data Index: 284206 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1323. Min Act: -0.0003

Data Index: 378122 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1308. Min Act: -0.0003

Data Index: 393711 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1280. Min Act: -0.0003

Data Index: 1286101 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1226. Min Act: -0.0003

Data Index: 827472 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1219. Min Act: -0.0003

Data Index: 620624 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1297. Min Act: -0.0003

Data Index: 442834 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1261. Min Act: -0.0003

Data Index: 773850 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1207. Min Act: -0.0004

Data Index: 38711 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1219. Min Act: -0.0003

Data Index: 803855 (C4 (Web Text))

Max Activating Token Index: 46