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

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

Neuron 2124 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.4187. Min Act: -0.0000

Data Index: 904048 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1294383 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1201023 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3883. Min Act: -0.0000

Data Index: 806606 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3638. Min Act: -0.0000

Data Index: 806848 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3602. Min Act: -0.0000

Data Index: 395078 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3719. Min Act: -0.0000

Data Index: 64337 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3694. Min Act: -0.0000

Data Index: 8352 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1351424 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3509. Min Act: -0.0000

Data Index: 1050627 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3834. Min Act: 0.0000

Data Index: 424264 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3569. Min Act: -0.0000

Data Index: 940299 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3524. Min Act: -0.0000

Data Index: 878525 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3590. Min Act: -0.0000

Data Index: 1100820 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3308. Min Act: 0.0000

Data Index: 1311318 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1181160 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3357. Min Act: -0.0000

Data Index: 551758 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1169559 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3340. Min Act: -0.0000

Data Index: 951282 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1330352 (C4 (Web Text))

Max Activating Token Index: 240