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

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

Neuron 2146 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.7407. Min Act: -0.0003

Data Index: 982417 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.7490. Min Act: -0.0003

Data Index: 204289 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.5727. Min Act: -0.0003

Data Index: 1171265 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6348. Min Act: -0.0003

Data Index: 686109 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6113. Min Act: -0.0003

Data Index: 1148839 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6026. Min Act: -0.0003

Data Index: 1322008 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6110. Min Act: -0.0003

Data Index: 977637 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6482. Min Act: -0.0003

Data Index: 435826 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.4868. Min Act: -0.0004

Data Index: 812494 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.5968. Min Act: -0.0003

Data Index: 1037814 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6296. Min Act: -0.0003

Data Index: 606622 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6339. Min Act: -0.0003

Data Index: 12337 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.5725. Min Act: -0.0003

Data Index: 63789 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.5812. Min Act: -0.0003

Data Index: 82666 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.5123. Min Act: -0.0003

Data Index: 897882 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.5783. Min Act: -0.0003

Data Index: 1151923 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.5440. Min Act: -0.0003

Data Index: 1329564 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.6031. Min Act: -0.0003

Data Index: 749901 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.4999. Min Act: -0.0003

Data Index: 1618928 (Python Code)

Max Activating Token Index: 442

Text #19

Max Range: 0.7490. Min Range: -0.7490

Max Act: 0.5468. Min Act: -0.0003

Data Index: 640232 (C4 (Web Text))

Max Activating Token Index: 658