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

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

Neuron 4800 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1202219 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2961. Min Act: -0.0000

Data Index: 793273 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2803. Min Act: -0.0000

Data Index: 51560 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1214133 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2697. Min Act: -0.0000

Data Index: 338562 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2550. Min Act: -0.0000

Data Index: 915905 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2623. Min Act: -0.0000

Data Index: 171220 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2343. Min Act: -0.0000

Data Index: 912109 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2515. Min Act: -0.0000

Data Index: 53680 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2481. Min Act: -0.0000

Data Index: 896270 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2465. Min Act: -0.0000

Data Index: 1327884 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2456. Min Act: -0.0000

Data Index: 784873 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2518. Min Act: -0.0000

Data Index: 790529 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2468. Min Act: -0.0000

Data Index: 628429 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2360. Min Act: -0.0000

Data Index: 824727 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2409. Min Act: -0.0000

Data Index: 229598 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2254. Min Act: -0.0000

Data Index: 1244239 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2297. Min Act: -0.0000

Data Index: 1336362 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1227280 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.3040. Min Range: -0.3040

Max Act: 0.2371. Min Act: -0.0000

Data Index: 32400 (C4 (Web Text))

Max Activating Token Index: 487