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

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

Neuron 4126 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: 4.9310. Min Range: -4.9310

Max Act: 4.9310. Min Act: -0.0000

Data Index: 1366752 (Python Code)

Max Activating Token Index: 820

Text #1

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.6247. Min Act: -0.0000

Data Index: 1526726 (Python Code)

Max Activating Token Index: 41

Text #2

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.0694. Min Act: -0.0000

Data Index: 1620335 (Python Code)

Max Activating Token Index: 265

Text #3

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.3781. Min Act: -0.0000

Data Index: 1548398 (Python Code)

Max Activating Token Index: 780

Text #4

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.0592. Min Act: -0.0000

Data Index: 1645669 (Python Code)

Max Activating Token Index: 435

Text #5

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.1670. Min Act: -0.0000

Data Index: 1435627 (Python Code)

Max Activating Token Index: 246

Text #6

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.1884. Min Act: -0.0000

Data Index: 1572227 (Python Code)

Max Activating Token Index: 539

Text #7

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.1643. Min Act: -0.0000

Data Index: 1605400 (Python Code)

Max Activating Token Index: 284

Text #8

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.0235. Min Act: -0.0000

Data Index: 1399799 (Python Code)

Max Activating Token Index: 343

Text #9

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.0319. Min Act: -0.0000

Data Index: 1545508 (Python Code)

Max Activating Token Index: 53

Text #10

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.0855. Min Act: -0.0000

Data Index: 1401541 (Python Code)

Max Activating Token Index: 606

Text #11

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.0467. Min Act: -0.0000

Data Index: 1652130 (Python Code)

Max Activating Token Index: 408

Text #12

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.0513. Min Act: -0.0000

Data Index: 1493259 (Python Code)

Max Activating Token Index: 713

Text #13

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.0561. Min Act: -0.0000

Data Index: 1454789 (Python Code)

Max Activating Token Index: 458

Text #14

Max Range: 4.9310. Min Range: -4.9310

Max Act: 3.9687. Min Act: -0.0000

Data Index: 1415127 (Python Code)

Max Activating Token Index: 334

Text #15

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.1497. Min Act: -0.0000

Data Index: 1411698 (Python Code)

Max Activating Token Index: 232

Text #16

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.0128. Min Act: -0.0000

Data Index: 1562213 (Python Code)

Max Activating Token Index: 660

Text #17

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.1632. Min Act: -0.0000

Data Index: 1526081 (Python Code)

Max Activating Token Index: 287

Text #18

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.0189. Min Act: -0.0000

Data Index: 1529334 (Python Code)

Max Activating Token Index: 582

Text #19

Max Range: 4.9310. Min Range: -4.9310

Max Act: 3.8449. Min Act: -0.0000

Data Index: 1545809 (Python Code)

Max Activating Token Index: 604