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

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

Neuron 5754 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1475. Min Act: -0.0000

Data Index: 1199637 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1437. Min Act: -0.0000

Data Index: 443382 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1420. Min Act: -0.0000

Data Index: 584397 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1353. Min Act: -0.0000

Data Index: 845995 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1408. Min Act: -0.0000

Data Index: 810838 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1402. Min Act: -0.0000

Data Index: 353994 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1283. Min Act: -0.0000

Data Index: 194114 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1259595 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1375. Min Act: -0.0000

Data Index: 999710 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1419. Min Act: -0.0000

Data Index: 550892 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1311. Min Act: -0.0000

Data Index: 400768 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1352. Min Act: -0.0000

Data Index: 1036736 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1381. Min Act: -0.0000

Data Index: 647917 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1331. Min Act: -0.0000

Data Index: 12458 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1277. Min Act: -0.0000

Data Index: 563976 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1363. Min Act: -0.0000

Data Index: 360362 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1275. Min Act: -0.0000

Data Index: 1256381 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1630387 (Python Code)

Max Activating Token Index: 214

Text #18

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1300. Min Act: -0.0000

Data Index: 620988 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1243. Min Act: -0.0000

Data Index: 642934 (C4 (Web Text))

Max Activating Token Index: 92