Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1284 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1480. Min Act: -0.0001

Data Index: 81558 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1505. Min Act: -0.0002

Data Index: 109281 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1492. Min Act: -0.0002

Data Index: 836140 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1348. Min Act: -0.0002

Data Index: 651647 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1395. Min Act: -0.0002

Data Index: 1096451 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1278. Min Act: -0.0002

Data Index: 358955 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1330. Min Act: -0.0002

Data Index: 377901 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1297. Min Act: -0.0002

Data Index: 505866 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1264. Min Act: -0.0002

Data Index: 429912 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1287. Min Act: -0.0002

Data Index: 1237347 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1268. Min Act: -0.0002

Data Index: 1234150 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1197. Min Act: -0.0001

Data Index: 714145 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1240. Min Act: -0.0002

Data Index: 771865 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1257. Min Act: -0.0001

Data Index: 55743 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1170. Min Act: -0.0001

Data Index: 772360 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1212. Min Act: -0.0001

Data Index: 266446 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1212. Min Act: -0.0002

Data Index: 236147 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1190. Min Act: -0.0002

Data Index: 288861 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1196. Min Act: -0.0002

Data Index: 459937 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1194. Min Act: -0.0002

Data Index: 94231 (C4 (Web Text))

Max Activating Token Index: 407