Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 303 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1127022 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1259712 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1447. Min Act: -0.0001

Data Index: 1112332 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1058757 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1342. Min Act: -0.0001

Data Index: 227200 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1288. Min Act: -0.0001

Data Index: 253869 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1155. Min Act: -0.0001

Data Index: 545463 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1267. Min Act: -0.0001

Data Index: 1266394 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1351. Min Act: -0.0001

Data Index: 145828 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1289. Min Act: -0.0001

Data Index: 99422 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1289. Min Act: -0.0001

Data Index: 625790 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1228. Min Act: -0.0001

Data Index: 1100516 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1266. Min Act: -0.0001

Data Index: 823357 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1262. Min Act: -0.0001

Data Index: 1098011 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1309. Min Act: -0.0001

Data Index: 745773 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1255. Min Act: -0.0001

Data Index: 862186 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1337. Min Act: -0.0001

Data Index: 1119741 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1296. Min Act: -0.0001

Data Index: 596872 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1276. Min Act: -0.0001

Data Index: 921169 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1424. Min Act: -0.0001

Data Index: 702372 (C4 (Web Text))

Max Activating Token Index: 854