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

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

Neuron 133 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1768. Min Act: -0.0001

Data Index: 810439 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1721. Min Act: -0.0001

Data Index: 1097560 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1582. Min Act: -0.0001

Data Index: 42221 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1509. Min Act: -0.0001

Data Index: 1348371 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1599. Min Act: -0.0001

Data Index: 824666 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1475. Min Act: -0.0001

Data Index: 363063 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1445. Min Act: -0.0001

Data Index: 474621 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1437. Min Act: -0.0001

Data Index: 741760 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1399. Min Act: -0.0001

Data Index: 517220 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1386. Min Act: -0.0001

Data Index: 295416 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1344693 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1364. Min Act: -0.0001

Data Index: 88256 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1255. Min Act: -0.0001

Data Index: 144241 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1267. Min Act: -0.0001

Data Index: 337088 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1360. Min Act: -0.0001

Data Index: 1035006 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1303. Min Act: -0.0001

Data Index: 788454 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1302. Min Act: -0.0001

Data Index: 824206 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1100599 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1322. Min Act: -0.0001

Data Index: 395984 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1262. Min Act: -0.0001

Data Index: 880764 (C4 (Web Text))

Max Activating Token Index: 460