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

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

Neuron 3133 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0490. Min Act: -0.0002

Data Index: 329760 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0546. Min Act: -0.0002

Data Index: 955121 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1031221 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0509. Min Act: -0.0002

Data Index: 291935 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0449. Min Act: -0.0002

Data Index: 98891 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0479. Min Act: -0.0002

Data Index: 328300 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0458. Min Act: -0.0002

Data Index: 765217 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0471. Min Act: -0.0002

Data Index: 487613 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0458. Min Act: -0.0002

Data Index: 780644 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1006013 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0522. Min Act: -0.0002

Data Index: 900688 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0433. Min Act: -0.0002

Data Index: 823103 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1224 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0351. Min Act: -0.0002

Data Index: 228323 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0448. Min Act: -0.0002

Data Index: 944346 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0435. Min Act: -0.0002

Data Index: 197029 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0433. Min Act: -0.0002

Data Index: 83677 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1122275 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0424. Min Act: -0.0002

Data Index: 210003 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0365. Min Act: -0.0002

Data Index: 685312 (C4 (Web Text))

Max Activating Token Index: 308