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

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

Neuron 308 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3319. Min Range: -1.3319

Max Act: 1.3319. Min Act: -0.0001

Data Index: 590458 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 1.3319. Min Range: -1.3319

Max Act: 1.2529. Min Act: -0.0001

Data Index: 603390 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 1.3319. Min Range: -1.3319

Max Act: 1.1715. Min Act: -0.0001

Data Index: 917149 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 1.3319. Min Range: -1.3319

Max Act: 1.1235. Min Act: -0.0001

Data Index: 582911 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 1.3319. Min Range: -1.3319

Max Act: 1.0776. Min Act: -0.0001

Data Index: 1169414 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 1.3319. Min Range: -1.3319

Max Act: 1.0778. Min Act: -0.0001

Data Index: 200050 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 1.3319. Min Range: -1.3319

Max Act: 1.0433. Min Act: -0.0001

Data Index: 89443 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 1.3319. Min Range: -1.3319

Max Act: 1.0386. Min Act: -0.0001

Data Index: 1151698 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 1.3319. Min Range: -1.3319

Max Act: 1.0068. Min Act: -0.0001

Data Index: 636421 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 1.3319. Min Range: -1.3319

Max Act: 0.9934. Min Act: -0.0001

Data Index: 1175190 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 1.3319. Min Range: -1.3319

Max Act: 0.9732. Min Act: -0.0001

Data Index: 1175638 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 1.3319. Min Range: -1.3319

Max Act: 0.9636. Min Act: -0.0001

Data Index: 532953 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 1.3319. Min Range: -1.3319

Max Act: 0.9777. Min Act: -0.0001

Data Index: 594361 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 1.3319. Min Range: -1.3319

Max Act: 0.9255. Min Act: -0.0001

Data Index: 672134 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 1.3319. Min Range: -1.3319

Max Act: 0.9265. Min Act: -0.0001

Data Index: 748296 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 1.3319. Min Range: -1.3319

Max Act: 0.8630. Min Act: -0.0001

Data Index: 1045521 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 1.3319. Min Range: -1.3319

Max Act: 0.9225. Min Act: -0.0001

Data Index: 465842 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 1.3319. Min Range: -1.3319

Max Act: 0.9149. Min Act: -0.0001

Data Index: 1219512 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 1.3319. Min Range: -1.3319

Max Act: 0.9157. Min Act: -0.0001

Data Index: 1295925 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 1.3319. Min Range: -1.3319

Max Act: 0.9089. Min Act: -0.0001

Data Index: 278105 (C4 (Web Text))

Max Activating Token Index: 526