Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3534 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1670. Min Act: -0.0000

Data Index: 249965 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1553. Min Act: -0.0000

Data Index: 924389 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1562. Min Act: -0.0000

Data Index: 433187 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1512. Min Act: -0.0000

Data Index: 990570 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1145522 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1427. Min Act: -0.0000

Data Index: 1018128 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1407. Min Act: -0.0000

Data Index: 236158 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1450. Min Act: -0.0000

Data Index: 808385 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1355. Min Act: -0.0000

Data Index: 365494 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1285. Min Act: -0.0000

Data Index: 432948 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1302. Min Act: -0.0000

Data Index: 1171557 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1110. Min Act: -0.0000

Data Index: 711544 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1338. Min Act: -0.0000

Data Index: 369911 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1420. Min Act: -0.0000

Data Index: 657053 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1220. Min Act: -0.0000

Data Index: 181689 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1163. Min Act: -0.0000

Data Index: 601734 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1162349 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1219. Min Act: -0.0000

Data Index: 774133 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1322. Min Act: -0.0000

Data Index: 35324 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1211. Min Act: -0.0000

Data Index: 912458 (C4 (Web Text))

Max Activating Token Index: 181