Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2527 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4665. Min Act: -0.0003

Data Index: 1358393 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4068. Min Act: -0.0003

Data Index: 1190037 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3960. Min Act: -0.0003

Data Index: 1221362 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3967. Min Act: -0.0003

Data Index: 224445 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3979. Min Act: -0.0003

Data Index: 853872 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.4116. Min Act: -0.0003

Data Index: 877750 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3687. Min Act: -0.0003

Data Index: 818959 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3444. Min Act: -0.0003

Data Index: 1304081 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3431. Min Act: -0.0003

Data Index: 906550 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3848. Min Act: -0.0003

Data Index: 1180801 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3965. Min Act: -0.0003

Data Index: 52626 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3320. Min Act: -0.0003

Data Index: 159087 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3568. Min Act: -0.0003

Data Index: 179942 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3372. Min Act: -0.0003

Data Index: 464596 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3363. Min Act: -0.0003

Data Index: 597597 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3598. Min Act: -0.0003

Data Index: 1354297 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3336. Min Act: -0.0003

Data Index: 41446 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3581. Min Act: -0.0003

Data Index: 128339 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3626. Min Act: -0.0003

Data Index: 60111 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.4665. Min Range: -0.4665

Max Act: 0.3256. Min Act: -0.0003

Data Index: 1275004 (C4 (Web Text))

Max Activating Token Index: 512