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

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

Neuron 4239 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1471. Min Act: -0.0002

Data Index: 1152587 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1440. Min Act: -0.0002

Data Index: 405537 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1436. Min Act: -0.0002

Data Index: 544173 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1486. Min Act: -0.0002

Data Index: 1106663 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1400. Min Act: -0.0002

Data Index: 252507 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1392. Min Act: -0.0002

Data Index: 359855 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1306. Min Act: -0.0002

Data Index: 195440 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1319. Min Act: -0.0002

Data Index: 70743 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1313. Min Act: -0.0002

Data Index: 1177593 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1291. Min Act: -0.0002

Data Index: 1052745 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1270. Min Act: -0.0002

Data Index: 1072645 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1300. Min Act: -0.0002

Data Index: 442811 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1237. Min Act: -0.0002

Data Index: 566766 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1222. Min Act: -0.0002

Data Index: 496134 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1211. Min Act: -0.0002

Data Index: 186276 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1169. Min Act: -0.0002

Data Index: 426621 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1166. Min Act: -0.0002

Data Index: 1259803 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1171. Min Act: -0.0002

Data Index: 766791 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1188. Min Act: -0.0002

Data Index: 551360 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1163. Min Act: -0.0002

Data Index: 709120 (C4 (Web Text))

Max Activating Token Index: 590