Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3477 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.9503. Min Act: -0.0001

Data Index: 1256038 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.9147. Min Act: -0.0001

Data Index: 483276 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.9280. Min Act: -0.0000

Data Index: 1192204 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.9219. Min Act: -0.0001

Data Index: 11628 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.9788. Min Act: -0.0000

Data Index: 502769 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.8532. Min Act: -0.0000

Data Index: 689183 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.8495. Min Act: -0.0001

Data Index: 605335 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.8730. Min Act: -0.0001

Data Index: 1058801 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.8279. Min Act: -0.0000

Data Index: 688222 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.8482. Min Act: -0.0001

Data Index: 794687 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.8088. Min Act: -0.0001

Data Index: 1124482 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.8340. Min Act: -0.0001

Data Index: 1276216 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.8029. Min Act: -0.0001

Data Index: 502837 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.7951. Min Act: -0.0001

Data Index: 1109761 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.7906. Min Act: -0.0001

Data Index: 931669 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.7293. Min Act: -0.0001

Data Index: 869669 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.7561. Min Act: -0.0001

Data Index: 1115736 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.7737. Min Act: -0.0001

Data Index: 1251134 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.7475. Min Act: -0.0001

Data Index: 221622 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.9788. Min Range: -0.9788

Max Act: 0.7715. Min Act: -0.0001

Data Index: 241232 (C4 (Web Text))

Max Activating Token Index: 440