Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4278 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6399. Min Range: -1.6399

Max Act: 1.6399. Min Act: -0.0000

Data Index: 1465513 (Python Code)

Max Activating Token Index: 994

Text #1

Max Range: 1.6399. Min Range: -1.6399

Max Act: 1.5200. Min Act: -0.0000

Data Index: 1475461 (Python Code)

Max Activating Token Index: 243

Text #2

Max Range: 1.6399. Min Range: -1.6399

Max Act: 1.3192. Min Act: -0.0000

Data Index: 1640843 (Python Code)

Max Activating Token Index: 110

Text #3

Max Range: 1.6399. Min Range: -1.6399

Max Act: 1.3772. Min Act: -0.0000

Data Index: 1423849 (Python Code)

Max Activating Token Index: 51

Text #4

Max Range: 1.6399. Min Range: -1.6399

Max Act: 1.2334. Min Act: -0.0000

Data Index: 1510101 (Python Code)

Max Activating Token Index: 228

Text #5

Max Range: 1.6399. Min Range: -1.6399

Max Act: 1.0851. Min Act: -0.0000

Data Index: 1650588 (Python Code)

Max Activating Token Index: 639

Text #6

Max Range: 1.6399. Min Range: -1.6399

Max Act: 1.1581. Min Act: -0.0000

Data Index: 1445967 (Python Code)

Max Activating Token Index: 459

Text #7

Max Range: 1.6399. Min Range: -1.6399

Max Act: 1.2912. Min Act: -0.0000

Data Index: 1602456 (Python Code)

Max Activating Token Index: 943

Text #8

Max Range: 1.6399. Min Range: -1.6399

Max Act: 1.1356. Min Act: -0.0000

Data Index: 1566228 (Python Code)

Max Activating Token Index: 106

Text #9

Max Range: 1.6399. Min Range: -1.6399

Max Act: 1.1237. Min Act: -0.0000

Data Index: 1531934 (Python Code)

Max Activating Token Index: 856

Text #10

Max Range: 1.6399. Min Range: -1.6399

Max Act: 1.0858. Min Act: -0.0000

Data Index: 1593851 (Python Code)

Max Activating Token Index: 772

Text #11

Max Range: 1.6399. Min Range: -1.6399

Max Act: 1.0835. Min Act: -0.0000

Data Index: 1522346 (Python Code)

Max Activating Token Index: 380

Text #12

Max Range: 1.6399. Min Range: -1.6399

Max Act: 1.0695. Min Act: -0.0000

Data Index: 1426408 (Python Code)

Max Activating Token Index: 671

Text #13

Max Range: 1.6399. Min Range: -1.6399

Max Act: 1.0776. Min Act: -0.0000

Data Index: 1585764 (Python Code)

Max Activating Token Index: 741

Text #14

Max Range: 1.6399. Min Range: -1.6399

Max Act: 0.9403. Min Act: -0.0000

Data Index: 1526845 (Python Code)

Max Activating Token Index: 284

Text #15

Max Range: 1.6399. Min Range: -1.6399

Max Act: 1.0535. Min Act: -0.0000

Data Index: 1402205 (Python Code)

Max Activating Token Index: 381

Text #16

Max Range: 1.6399. Min Range: -1.6399

Max Act: 1.1139. Min Act: -0.0000

Data Index: 1458294 (Python Code)

Max Activating Token Index: 163

Text #17

Max Range: 1.6399. Min Range: -1.6399

Max Act: 1.0405. Min Act: -0.0000

Data Index: 1546031 (Python Code)

Max Activating Token Index: 884

Text #18

Max Range: 1.6399. Min Range: -1.6399

Max Act: 0.9401. Min Act: -0.0000

Data Index: 1634768 (Python Code)

Max Activating Token Index: 913

Text #19

Max Range: 1.6399. Min Range: -1.6399

Max Act: 1.0731. Min Act: -0.0000

Data Index: 1540670 (Python Code)

Max Activating Token Index: 516