Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4653 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3486. Min Act: -0.0000

Data Index: 671909 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1130562 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3200. Min Act: -0.0000

Data Index: 900059 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2947. Min Act: -0.0000

Data Index: 679311 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2866. Min Act: -0.0000

Data Index: 714014 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2640. Min Act: -0.0000

Data Index: 334533 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1352426 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2481. Min Act: -0.0000

Data Index: 464938 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2617. Min Act: -0.0000

Data Index: 896113 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2639. Min Act: -0.0000

Data Index: 1329990 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2420. Min Act: -0.0000

Data Index: 300347 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2620. Min Act: -0.0000

Data Index: 138840 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2427. Min Act: -0.0000

Data Index: 644680 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1227704 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2385. Min Act: -0.0000

Data Index: 133947 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2477. Min Act: -0.0000

Data Index: 234939 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2431. Min Act: -0.0000

Data Index: 151934 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2256. Min Act: -0.0000

Data Index: 903434 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2591. Min Act: -0.0000

Data Index: 837895 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2347. Min Act: -0.0000

Data Index: 457501 (C4 (Web Text))

Max Activating Token Index: 616