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

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

Neuron 1286 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8196. Min Range: -6.8196

Max Act: 6.8196. Min Act: -0.0000

Data Index: 173852 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 6.8196. Min Range: -6.8196

Max Act: 6.4924. Min Act: -0.0000

Data Index: 477929 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 6.8196. Min Range: -6.8196

Max Act: 5.8745. Min Act: -0.0000

Data Index: 1095280 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 6.8196. Min Range: -6.8196

Max Act: 5.6528. Min Act: -0.0000

Data Index: 791394 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 6.8196. Min Range: -6.8196

Max Act: 5.1363. Min Act: -0.0000

Data Index: 70651 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 6.8196. Min Range: -6.8196

Max Act: 5.2369. Min Act: -0.0000

Data Index: 1116088 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 6.8196. Min Range: -6.8196

Max Act: 5.2327. Min Act: -0.0000

Data Index: 301022 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 6.8196. Min Range: -6.8196

Max Act: 5.0058. Min Act: -0.0000

Data Index: 1251872 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 6.8196. Min Range: -6.8196

Max Act: 5.1614. Min Act: 0.0000

Data Index: 840111 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 6.8196. Min Range: -6.8196

Max Act: 4.7959. Min Act: -0.0000

Data Index: 743812 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 6.8196. Min Range: -6.8196

Max Act: 4.9316. Min Act: -0.0000

Data Index: 1150923 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 6.8196. Min Range: -6.8196

Max Act: 4.7529. Min Act: -0.0000

Data Index: 697060 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 6.8196. Min Range: -6.8196

Max Act: 5.0613. Min Act: 0.0000

Data Index: 614278 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 6.8196. Min Range: -6.8196

Max Act: 4.8730. Min Act: -0.0000

Data Index: 1008707 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 6.8196. Min Range: -6.8196

Max Act: 4.8457. Min Act: 0.0000

Data Index: 395264 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 6.8196. Min Range: -6.8196

Max Act: 4.6708. Min Act: 0.0000

Data Index: 893715 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 6.8196. Min Range: -6.8196

Max Act: 4.9982. Min Act: -0.0000

Data Index: 97945 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 6.8196. Min Range: -6.8196

Max Act: 4.7800. Min Act: -0.0000

Data Index: 848748 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 6.8196. Min Range: -6.8196

Max Act: 4.7587. Min Act: -0.0000

Data Index: 431483 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 6.8196. Min Range: -6.8196

Max Act: 4.7330. Min Act: -0.0000

Data Index: 964304 (C4 (Web Text))

Max Activating Token Index: 636