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

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

Neuron 4940 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.2145. Min Act: -0.0000

Data Index: 909126 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.1685. Min Act: -0.0000

Data Index: 956033 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.1729. Min Act: -0.0000

Data Index: 520514 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.1621. Min Act: -0.0000

Data Index: 775457 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.1697. Min Act: -0.0000

Data Index: 1258381 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.1559. Min Act: -0.0000

Data Index: 140093 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.1547. Min Act: -0.0000

Data Index: 1301725 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.1500. Min Act: -0.0000

Data Index: 896751 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.1408. Min Act: -0.0000

Data Index: 423361 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.1313. Min Act: -0.0000

Data Index: 611347 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.1334. Min Act: -0.0000

Data Index: 985228 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.1378. Min Act: -0.0000

Data Index: 115672 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1219743 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.1352. Min Act: -0.0000

Data Index: 8762 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.1389. Min Act: -0.0000

Data Index: 180891 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1159310 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.1313. Min Act: -0.0000

Data Index: 1348056 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.1222. Min Act: -0.0000

Data Index: 768160 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.1331. Min Act: -0.0000

Data Index: 787516 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.2145. Min Range: -0.2145

Max Act: 0.1325. Min Act: -0.0000

Data Index: 151050 (C4 (Web Text))

Max Activating Token Index: 922