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

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

Neuron 3246 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3271. Min Range: -2.3271

Max Act: 2.3271. Min Act: -0.0000

Data Index: 1260937 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 2.3271. Min Range: -2.3271

Max Act: 2.1411. Min Act: -0.0000

Data Index: 558197 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 2.3271. Min Range: -2.3271

Max Act: 1.7826. Min Act: -0.0000

Data Index: 720877 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 2.3271. Min Range: -2.3271

Max Act: 1.7563. Min Act: -0.0000

Data Index: 759039 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 2.3271. Min Range: -2.3271

Max Act: 1.6241. Min Act: -0.0000

Data Index: 1147755 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 2.3271. Min Range: -2.3271

Max Act: 1.5970. Min Act: -0.0000

Data Index: 751193 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 2.3271. Min Range: -2.3271

Max Act: 1.5898. Min Act: -0.0000

Data Index: 638428 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 2.3271. Min Range: -2.3271

Max Act: 1.6461. Min Act: -0.0000

Data Index: 367034 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 2.3271. Min Range: -2.3271

Max Act: 1.4361. Min Act: -0.0000

Data Index: 260897 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 2.3271. Min Range: -2.3271

Max Act: 1.5211. Min Act: -0.0000

Data Index: 1043503 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 2.3271. Min Range: -2.3271

Max Act: 1.5530. Min Act: -0.0000

Data Index: 137744 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 2.3271. Min Range: -2.3271

Max Act: 1.4627. Min Act: -0.0000

Data Index: 867208 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 2.3271. Min Range: -2.3271

Max Act: 1.4424. Min Act: -0.0000

Data Index: 1126882 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 2.3271. Min Range: -2.3271

Max Act: 1.4031. Min Act: 0.0000

Data Index: 243716 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 2.3271. Min Range: -2.3271

Max Act: 1.2446. Min Act: -0.0000

Data Index: 747710 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 2.3271. Min Range: -2.3271

Max Act: 1.3000. Min Act: -0.0000

Data Index: 1141951 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 2.3271. Min Range: -2.3271

Max Act: 1.2810. Min Act: -0.0000

Data Index: 66412 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 2.3271. Min Range: -2.3271

Max Act: 1.1766. Min Act: -0.0000

Data Index: 338377 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 2.3271. Min Range: -2.3271

Max Act: 1.1892. Min Act: -0.0000

Data Index: 46009 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 2.3271. Min Range: -2.3271

Max Act: 1.1784. Min Act: -0.0000

Data Index: 18388 (C4 (Web Text))

Max Activating Token Index: 621