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

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

Neuron 3433 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3177. Min Range: -2.3177

Max Act: 2.3177. Min Act: -0.0000

Data Index: 1401032 (Python Code)

Max Activating Token Index: 212

Text #1

Max Range: 2.3177. Min Range: -2.3177

Max Act: 2.2912. Min Act: -0.0000

Data Index: 1494024 (Python Code)

Max Activating Token Index: 261

Text #2

Max Range: 2.3177. Min Range: -2.3177

Max Act: 2.1554. Min Act: -0.0000

Data Index: 1524714 (Python Code)

Max Activating Token Index: 213

Text #3

Max Range: 2.3177. Min Range: -2.3177

Max Act: 2.1672. Min Act: -0.0000

Data Index: 252218 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 2.3177. Min Range: -2.3177

Max Act: 1.9395. Min Act: -0.0000

Data Index: 698962 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 2.3177. Min Range: -2.3177

Max Act: 1.7573. Min Act: -0.0000

Data Index: 1434233 (Python Code)

Max Activating Token Index: 712

Text #6

Max Range: 2.3177. Min Range: -2.3177

Max Act: 1.6380. Min Act: -0.0000

Data Index: 1398560 (Python Code)

Max Activating Token Index: 84

Text #7

Max Range: 2.3177. Min Range: -2.3177

Max Act: 1.8090. Min Act: -0.0000

Data Index: 578109 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 2.3177. Min Range: -2.3177

Max Act: 1.8078. Min Act: -0.0000

Data Index: 1397613 (Python Code)

Max Activating Token Index: 460

Text #9

Max Range: 2.3177. Min Range: -2.3177

Max Act: 1.8038. Min Act: -0.0000

Data Index: 1401525 (Python Code)

Max Activating Token Index: 103

Text #10

Max Range: 2.3177. Min Range: -2.3177

Max Act: 1.8036. Min Act: -0.0000

Data Index: 1432777 (Python Code)

Max Activating Token Index: 9

Text #11

Max Range: 2.3177. Min Range: -2.3177

Max Act: 1.7266. Min Act: -0.0000

Data Index: 1532771 (Python Code)

Max Activating Token Index: 19

Text #12

Max Range: 2.3177. Min Range: -2.3177

Max Act: 1.8105. Min Act: -0.0000

Data Index: 1630961 (Python Code)

Max Activating Token Index: 142

Text #13

Max Range: 2.3177. Min Range: -2.3177

Max Act: 1.5758. Min Act: -0.0000

Data Index: 336096 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 2.3177. Min Range: -2.3177

Max Act: 1.7797. Min Act: -0.0000

Data Index: 1559654 (Python Code)

Max Activating Token Index: 749

Text #15

Max Range: 2.3177. Min Range: -2.3177

Max Act: 1.6352. Min Act: -0.0000

Data Index: 939852 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 2.3177. Min Range: -2.3177

Max Act: 1.6225. Min Act: -0.0000

Data Index: 1500392 (Python Code)

Max Activating Token Index: 695

Text #17

Max Range: 2.3177. Min Range: -2.3177

Max Act: 1.5326. Min Act: -0.0000

Data Index: 1570571 (Python Code)

Max Activating Token Index: 124

Text #18

Max Range: 2.3177. Min Range: -2.3177

Max Act: 1.7523. Min Act: -0.0000

Data Index: 1579037 (Python Code)

Max Activating Token Index: 748

Text #19

Max Range: 2.3177. Min Range: -2.3177

Max Act: 1.6479. Min Act: -0.0000

Data Index: 1455719 (Python Code)

Max Activating Token Index: 344