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

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

Neuron 2244 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1705. Min Range: -2.1705

Max Act: 2.1705. Min Act: -0.0000

Data Index: 1249069 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 2.1705. Min Range: -2.1705

Max Act: 2.0293. Min Act: -0.0000

Data Index: 106515 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 2.1705. Min Range: -2.1705

Max Act: 1.8945. Min Act: -0.0000

Data Index: 798035 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 2.1705. Min Range: -2.1705

Max Act: 1.8768. Min Act: -0.0000

Data Index: 614485 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 2.1705. Min Range: -2.1705

Max Act: 1.8033. Min Act: -0.0000

Data Index: 392186 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 2.1705. Min Range: -2.1705

Max Act: 1.8914. Min Act: -0.0000

Data Index: 1258872 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 2.1705. Min Range: -2.1705

Max Act: 1.7630. Min Act: -0.0000

Data Index: 782403 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 2.1705. Min Range: -2.1705

Max Act: 1.7287. Min Act: -0.0000

Data Index: 906323 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 2.1705. Min Range: -2.1705

Max Act: 1.6930. Min Act: -0.0000

Data Index: 856155 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 2.1705. Min Range: -2.1705

Max Act: 1.6679. Min Act: -0.0000

Data Index: 801189 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 2.1705. Min Range: -2.1705

Max Act: 1.6747. Min Act: -0.0000

Data Index: 928854 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 2.1705. Min Range: -2.1705

Max Act: 1.7263. Min Act: -0.0000

Data Index: 239948 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 2.1705. Min Range: -2.1705

Max Act: 1.6369. Min Act: -0.0000

Data Index: 471598 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 2.1705. Min Range: -2.1705

Max Act: 1.6194. Min Act: -0.0000

Data Index: 2584 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 2.1705. Min Range: -2.1705

Max Act: 1.5274. Min Act: -0.0000

Data Index: 570449 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 2.1705. Min Range: -2.1705

Max Act: 1.6781. Min Act: -0.0000

Data Index: 340761 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 2.1705. Min Range: -2.1705

Max Act: 1.5580. Min Act: -0.0000

Data Index: 786544 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 2.1705. Min Range: -2.1705

Max Act: 1.5377. Min Act: -0.0000

Data Index: 96211 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 2.1705. Min Range: -2.1705

Max Act: 1.5394. Min Act: -0.0000

Data Index: 465249 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 2.1705. Min Range: -2.1705

Max Act: 1.5304. Min Act: -0.0000

Data Index: 1035003 (C4 (Web Text))

Max Activating Token Index: 562