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

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

Neuron 5485 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5216. Min Range: -3.5216

Max Act: 3.5216. Min Act: -0.0000

Data Index: 1029147 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 3.5216. Min Range: -3.5216

Max Act: 2.7222. Min Act: -0.0000

Data Index: 1003753 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 3.5216. Min Range: -3.5216

Max Act: 2.8124. Min Act: -0.0000

Data Index: 1123757 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 3.5216. Min Range: -3.5216

Max Act: 2.4860. Min Act: -0.0000

Data Index: 408198 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 3.5216. Min Range: -3.5216

Max Act: 2.4261. Min Act: -0.0000

Data Index: 456212 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 3.5216. Min Range: -3.5216

Max Act: 2.3280. Min Act: -0.0000

Data Index: 942213 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 3.5216. Min Range: -3.5216

Max Act: 2.1123. Min Act: -0.0000

Data Index: 418510 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 3.5216. Min Range: -3.5216

Max Act: 2.0678. Min Act: -0.0000

Data Index: 746065 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 3.5216. Min Range: -3.5216

Max Act: 2.0538. Min Act: -0.0000

Data Index: 470438 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 3.5216. Min Range: -3.5216

Max Act: 1.8990. Min Act: -0.0000

Data Index: 794629 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 3.5216. Min Range: -3.5216

Max Act: 2.0059. Min Act: -0.0000

Data Index: 945952 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 3.5216. Min Range: -3.5216

Max Act: 2.0041. Min Act: -0.0000

Data Index: 902629 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 3.5216. Min Range: -3.5216

Max Act: 1.7494. Min Act: -0.0000

Data Index: 1282188 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 3.5216. Min Range: -3.5216

Max Act: 1.7266. Min Act: -0.0000

Data Index: 870241 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 3.5216. Min Range: -3.5216

Max Act: 1.7112. Min Act: -0.0000

Data Index: 14780 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 3.5216. Min Range: -3.5216

Max Act: 1.7662. Min Act: -0.0000

Data Index: 1303017 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 3.5216. Min Range: -3.5216

Max Act: 1.7103. Min Act: -0.0000

Data Index: 875395 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 3.5216. Min Range: -3.5216

Max Act: 1.8629. Min Act: -0.0000

Data Index: 258685 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 3.5216. Min Range: -3.5216

Max Act: 1.7543. Min Act: -0.0000

Data Index: 1261773 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 3.5216. Min Range: -3.5216

Max Act: 1.7301. Min Act: -0.0000

Data Index: 1025179 (C4 (Web Text))

Max Activating Token Index: 938