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

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

Neuron 4768 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.5537. Min Act: -0.0002

Data Index: 975046 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.5206. Min Act: -0.0002

Data Index: 1119078 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.4682. Min Act: -0.0002

Data Index: 777295 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.4987. Min Act: -0.0002

Data Index: 677407 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.5061. Min Act: -0.0002

Data Index: 652432 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.4893. Min Act: -0.0002

Data Index: 454388 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.4507. Min Act: -0.0002

Data Index: 657435 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.4447. Min Act: -0.0002

Data Index: 978170 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.4433. Min Act: -0.0002

Data Index: 29776 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.4382. Min Act: -0.0002

Data Index: 720811 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.4282. Min Act: -0.0002

Data Index: 1321217 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.4280. Min Act: -0.0002

Data Index: 545921 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.4587. Min Act: -0.0002

Data Index: 766817 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.4174. Min Act: -0.0002

Data Index: 597724 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.4018. Min Act: -0.0002

Data Index: 68852 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.4278. Min Act: -0.0002

Data Index: 1300104 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.4121. Min Act: -0.0002

Data Index: 1321937 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.4221. Min Act: -0.0002

Data Index: 436716 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.3747. Min Act: -0.0002

Data Index: 87894 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.3580. Min Act: -0.0002

Data Index: 210026 (C4 (Web Text))

Max Activating Token Index: 849