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

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

Neuron 812 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0478. Min Act: -0.0002

Data Index: 303767 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1322878 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0419. Min Act: -0.0002

Data Index: 790326 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0376. Min Act: -0.0002

Data Index: 51089 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1423199 (Python Code)

Max Activating Token Index: 291

Text #5

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1277268 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1524151 (Python Code)

Max Activating Token Index: 178

Text #7

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0337. Min Act: -0.0002

Data Index: 996906 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0320. Min Act: -0.0002

Data Index: 52952 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1496578 (Python Code)

Max Activating Token Index: 201

Text #10

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1572151 (Python Code)

Max Activating Token Index: 553

Text #11

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1563835 (Python Code)

Max Activating Token Index: 247

Text #12

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1602768 (Python Code)

Max Activating Token Index: 96

Text #13

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1401201 (Python Code)

Max Activating Token Index: 197

Text #14

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1584823 (Python Code)

Max Activating Token Index: 725

Text #15

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1578013 (Python Code)

Max Activating Token Index: 72

Text #16

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0301. Min Act: -0.0002

Data Index: 290026 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0297. Min Act: -0.0002

Data Index: 891395 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1425355 (Python Code)

Max Activating Token Index: 49

Text #19

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1257724 (C4 (Web Text))

Max Activating Token Index: 188