Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 905 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1795. Min Act: -0.0001

Data Index: 87868 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1583. Min Act: -0.0001

Data Index: 502244 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1646. Min Act: -0.0000

Data Index: 809871 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1475. Min Act: -0.0000

Data Index: 289087 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1364. Min Act: -0.0001

Data Index: 154869 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1370. Min Act: -0.0001

Data Index: 1026723 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1261. Min Act: -0.0001

Data Index: 225739 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1385. Min Act: -0.0000

Data Index: 1451020 (Python Code)

Max Activating Token Index: 116

Text #8

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1370. Min Act: -0.0001

Data Index: 643951 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1293. Min Act: -0.0000

Data Index: 367950 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1339. Min Act: -0.0000

Data Index: 84186 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1415. Min Act: -0.0001

Data Index: 1190526 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1318. Min Act: -0.0000

Data Index: 75913 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1260. Min Act: -0.0000

Data Index: 1334344 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1359349 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1297. Min Act: -0.0001

Data Index: 1113858 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1223. Min Act: -0.0001

Data Index: 280381 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1232. Min Act: -0.0000

Data Index: 756174 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1188. Min Act: -0.0001

Data Index: 176611 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.1795. Min Range: -0.1795

Max Act: 0.1214. Min Act: -0.0000

Data Index: 565347 (C4 (Web Text))

Max Activating Token Index: 776