Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 269 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1491. Min Act: -0.0002

Data Index: 349693 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1485. Min Act: -0.0002

Data Index: 739076 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1507. Min Act: -0.0002

Data Index: 201453 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1440. Min Act: -0.0002

Data Index: 817548 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1405. Min Act: -0.0002

Data Index: 321317 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1515. Min Act: -0.0002

Data Index: 266283 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1351. Min Act: -0.0002

Data Index: 817462 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1312. Min Act: -0.0002

Data Index: 549058 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1359. Min Act: -0.0002

Data Index: 765576 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1369. Min Act: -0.0002

Data Index: 55833 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1296. Min Act: -0.0002

Data Index: 350916 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1431. Min Act: -0.0002

Data Index: 1161372 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1390. Min Act: -0.0002

Data Index: 80698 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1325. Min Act: -0.0002

Data Index: 856616 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1338. Min Act: -0.0002

Data Index: 1098751 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1274. Min Act: -0.0002

Data Index: 869734 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1327. Min Act: -0.0002

Data Index: 143491 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1301. Min Act: -0.0002

Data Index: 373791 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1237. Min Act: -0.0002

Data Index: 1204893 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1291. Min Act: -0.0002

Data Index: 1222924 (C4 (Web Text))

Max Activating Token Index: 34