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

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

Neuron 3149 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: 0.1467. Min Range: -0.1467

Max Act: 0.1442. Min Act: -0.0001

Data Index: 1342204 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1467. Min Act: -0.0002

Data Index: 230946 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1406. Min Act: -0.0001

Data Index: 786996 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1022436 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1320. Min Act: -0.0002

Data Index: 621200 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1147. Min Act: -0.0001

Data Index: 372388 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1295. Min Act: -0.0002

Data Index: 820248 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1197. Min Act: -0.0001

Data Index: 162260 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1362. Min Act: -0.0001

Data Index: 270722 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1301. Min Act: -0.0001

Data Index: 878031 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1338. Min Act: -0.0002

Data Index: 195009 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1196. Min Act: -0.0001

Data Index: 1171048 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1254. Min Act: -0.0002

Data Index: 833257 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1204. Min Act: -0.0001

Data Index: 574969 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1242. Min Act: -0.0001

Data Index: 399625 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1159. Min Act: -0.0002

Data Index: 1252291 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1283. Min Act: -0.0002

Data Index: 20548 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1238. Min Act: -0.0002

Data Index: 1247943 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1144. Min Act: -0.0001

Data Index: 1080392 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1233. Min Act: -0.0002

Data Index: 1030924 (C4 (Web Text))

Max Activating Token Index: 481