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

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

Neuron 332 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.8292. Min Act: -0.0000

Data Index: 138084 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.5981. Min Act: -0.0000

Data Index: 1279112 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.5716. Min Act: -0.0000

Data Index: 464680 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.5638. Min Act: -0.0000

Data Index: 1151057 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.5716. Min Act: -0.0000

Data Index: 729163 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.5000. Min Act: -0.0000

Data Index: 73408 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.5833. Min Act: -0.0000

Data Index: 227301 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.5708. Min Act: -0.0000

Data Index: 367695 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.4827. Min Act: -0.0000

Data Index: 115092 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.6372. Min Act: -0.0000

Data Index: 1303058 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.4549. Min Act: -0.0000

Data Index: 118680 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.4301. Min Act: -0.0000

Data Index: 1187352 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.4040. Min Act: -0.0000

Data Index: 501600 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.3907. Min Act: -0.0000

Data Index: 276668 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.5447. Min Act: -0.0000

Data Index: 1023705 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.4476. Min Act: -0.0000

Data Index: 908545 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.4629. Min Act: -0.0000

Data Index: 100277 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.3702. Min Act: -0.0000

Data Index: 361344 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.4393. Min Act: -0.0000

Data Index: 833012 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 1.8292. Min Range: -1.8292

Max Act: 1.3616. Min Act: -0.0000

Data Index: 768581 (C4 (Web Text))

Max Activating Token Index: 163