Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1579 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3953. Min Range: -1.3953

Max Act: 1.3953. Min Act: -0.0001

Data Index: 1376922 (Python Code)

Max Activating Token Index: 576

Text #1

Max Range: 1.3953. Min Range: -1.3953

Max Act: 1.2604. Min Act: -0.0000

Data Index: 778747 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 1.3953. Min Range: -1.3953

Max Act: 1.2183. Min Act: -0.0001

Data Index: 1506780 (Python Code)

Max Activating Token Index: 485

Text #3

Max Range: 1.3953. Min Range: -1.3953

Max Act: 1.1712. Min Act: -0.0001

Data Index: 1623963 (Python Code)

Max Activating Token Index: 571

Text #4

Max Range: 1.3953. Min Range: -1.3953

Max Act: 1.1332. Min Act: -0.0001

Data Index: 1524966 (Python Code)

Max Activating Token Index: 8

Text #5

Max Range: 1.3953. Min Range: -1.3953

Max Act: 1.1391. Min Act: -0.0001

Data Index: 1480827 (Python Code)

Max Activating Token Index: 275

Text #6

Max Range: 1.3953. Min Range: -1.3953

Max Act: 1.0870. Min Act: -0.0001

Data Index: 1540708 (Python Code)

Max Activating Token Index: 484

Text #7

Max Range: 1.3953. Min Range: -1.3953

Max Act: 1.0569. Min Act: -0.0000

Data Index: 871965 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 1.3953. Min Range: -1.3953

Max Act: 1.0195. Min Act: -0.0000

Data Index: 1085103 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 1.3953. Min Range: -1.3953

Max Act: 1.0171. Min Act: -0.0001

Data Index: 260618 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 1.3953. Min Range: -1.3953

Max Act: 1.0426. Min Act: -0.0001

Data Index: 1384925 (Python Code)

Max Activating Token Index: 355

Text #11

Max Range: 1.3953. Min Range: -1.3953

Max Act: 1.0207. Min Act: -0.0000

Data Index: 247475 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 1.3953. Min Range: -1.3953

Max Act: 0.9866. Min Act: -0.0001

Data Index: 721435 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 1.3953. Min Range: -1.3953

Max Act: 0.9227. Min Act: -0.0000

Data Index: 662537 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 1.3953. Min Range: -1.3953

Max Act: 0.9427. Min Act: -0.0001

Data Index: 1052660 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 1.3953. Min Range: -1.3953

Max Act: 0.9701. Min Act: -0.0001

Data Index: 529429 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 1.3953. Min Range: -1.3953

Max Act: 0.9302. Min Act: -0.0000

Data Index: 1224264 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 1.3953. Min Range: -1.3953

Max Act: 1.0083. Min Act: -0.0001

Data Index: 1490714 (Python Code)

Max Activating Token Index: 325

Text #18

Max Range: 1.3953. Min Range: -1.3953

Max Act: 0.9184. Min Act: -0.0001

Data Index: 880206 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 1.3953. Min Range: -1.3953

Max Act: 0.9745. Min Act: -0.0001

Data Index: 1527576 (Python Code)

Max Activating Token Index: 895