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

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

Neuron 2217 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1911. Min Act: -0.0001

Data Index: 137680 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1370. Min Act: -0.0001

Data Index: 474780 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1435. Min Act: -0.0001

Data Index: 299741 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1460. Min Act: -0.0001

Data Index: 259875 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1423. Min Act: -0.0001

Data Index: 1100336 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1410. Min Act: -0.0001

Data Index: 332771 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1291. Min Act: -0.0001

Data Index: 192825 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1335. Min Act: -0.0001

Data Index: 1288210 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1383. Min Act: -0.0001

Data Index: 214037 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1181. Min Act: -0.0002

Data Index: 569292 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1163. Min Act: -0.0002

Data Index: 218051 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1270. Min Act: -0.0001

Data Index: 1091087 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1219. Min Act: -0.0001

Data Index: 880332 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1148. Min Act: -0.0002

Data Index: 50913 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1183. Min Act: -0.0001

Data Index: 301542 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1165. Min Act: -0.0002

Data Index: 45503 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1248. Min Act: -0.0001

Data Index: 511576 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1213. Min Act: -0.0001

Data Index: 140172 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1153. Min Act: -0.0001

Data Index: 471997 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1169. Min Act: -0.0001

Data Index: 522493 (C4 (Web Text))

Max Activating Token Index: 473