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

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

Neuron 1373 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2820. Min Act: -0.0001

Data Index: 349448 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2797. Min Act: -0.0001

Data Index: 706065 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2760. Min Act: -0.0001

Data Index: 51886 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2740. Min Act: -0.0001

Data Index: 198429 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2638. Min Act: -0.0001

Data Index: 640078 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2632. Min Act: -0.0001

Data Index: 574860 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2647. Min Act: -0.0001

Data Index: 145929 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2750. Min Act: -0.0001

Data Index: 728581 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2734. Min Act: -0.0001

Data Index: 513365 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2623. Min Act: -0.0001

Data Index: 155288 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2465. Min Act: -0.0001

Data Index: 1192845 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2382. Min Act: -0.0001

Data Index: 237204 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2509. Min Act: -0.0001

Data Index: 614022 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2698. Min Act: -0.0001

Data Index: 1159511 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2359. Min Act: -0.0001

Data Index: 1230701 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2335. Min Act: -0.0001

Data Index: 110670 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2318. Min Act: -0.0001

Data Index: 638953 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2495. Min Act: -0.0000

Data Index: 511413 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2398. Min Act: -0.0001

Data Index: 875275 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2420. Min Act: -0.0001

Data Index: 606401 (C4 (Web Text))

Max Activating Token Index: 131