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

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

Neuron 4058 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.9248. Min Act: -0.0001

Data Index: 864906 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8048. Min Act: -0.0002

Data Index: 840897 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8082. Min Act: -0.0001

Data Index: 690101 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.7555. Min Act: -0.0002

Data Index: 791232 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.7492. Min Act: -0.0002

Data Index: 593548 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.7324. Min Act: -0.0001

Data Index: 21053 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.7204. Min Act: -0.0001

Data Index: 610741 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6936. Min Act: -0.0001

Data Index: 1287873 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6582. Min Act: -0.0001

Data Index: 387814 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6841. Min Act: -0.0001

Data Index: 393669 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6624. Min Act: -0.0002

Data Index: 364691 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6640. Min Act: -0.0001

Data Index: 1175851 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6797. Min Act: -0.0002

Data Index: 715889 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6404. Min Act: -0.0001

Data Index: 930178 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6572. Min Act: -0.0002

Data Index: 228110 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6715. Min Act: -0.0001

Data Index: 961125 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.5241. Min Act: -0.0001

Data Index: 92937 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6168. Min Act: -0.0001

Data Index: 779804 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6510. Min Act: -0.0002

Data Index: 434626 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.5557. Min Act: -0.0001

Data Index: 421167 (C4 (Web Text))

Max Activating Token Index: 569