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

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

Neuron 492 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0385. Min Range: -1.0385

Max Act: 1.0385. Min Act: -0.0000

Data Index: 163932 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.9137. Min Act: -0.0000

Data Index: 426282 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.8714. Min Act: -0.0000

Data Index: 574712 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.8347. Min Act: -0.0000

Data Index: 404032 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.8033. Min Act: -0.0000

Data Index: 940544 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.8261. Min Act: -0.0000

Data Index: 648205 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.7785. Min Act: -0.0000

Data Index: 833536 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.7100. Min Act: -0.0000

Data Index: 1109128 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.7573. Min Act: -0.0000

Data Index: 102697 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.7626. Min Act: -0.0000

Data Index: 145179 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.7196. Min Act: -0.0000

Data Index: 245932 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.7204. Min Act: -0.0000

Data Index: 64741 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1251995 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6763. Min Act: -0.0000

Data Index: 516581 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6911. Min Act: -0.0000

Data Index: 1186851 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6897. Min Act: -0.0000

Data Index: 739409 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1142975 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1279081 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6469. Min Act: -0.0000

Data Index: 804536 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 1.0385. Min Range: -1.0385

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1184551 (C4 (Web Text))

Max Activating Token Index: 98