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

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

Neuron 1211 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1548. Min Act: -0.0001

Data Index: 709351 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1561. Min Act: -0.0001

Data Index: 1286684 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1475. Min Act: -0.0001

Data Index: 1173510 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1319. Min Act: -0.0001

Data Index: 879702 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1402. Min Act: -0.0001

Data Index: 203241 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1355. Min Act: -0.0000

Data Index: 1015028 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1348. Min Act: -0.0001

Data Index: 732935 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1273. Min Act: -0.0001

Data Index: 665542 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1344. Min Act: -0.0001

Data Index: 768005 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1256. Min Act: -0.0001

Data Index: 406433 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1287. Min Act: -0.0001

Data Index: 27987 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1240. Min Act: -0.0001

Data Index: 1031907 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1298. Min Act: -0.0001

Data Index: 950583 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1322. Min Act: -0.0001

Data Index: 1091308 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1193. Min Act: -0.0001

Data Index: 271546 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1270. Min Act: -0.0001

Data Index: 902631 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1253. Min Act: -0.0001

Data Index: 430978 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1240. Min Act: -0.0001

Data Index: 248148 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1123. Min Act: -0.0001

Data Index: 474534 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1230. Min Act: -0.0001

Data Index: 43153 (C4 (Web Text))

Max Activating Token Index: 896