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

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

Neuron 4606 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6818. Min Act: -0.0000

Data Index: 319452 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6159. Min Act: -0.0000

Data Index: 52108 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1162227 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5373. Min Act: -0.0000

Data Index: 806273 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1074302 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5009. Min Act: -0.0000

Data Index: 321295 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1252209 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4951. Min Act: -0.0000

Data Index: 888287 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4803. Min Act: -0.0000

Data Index: 889596 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1200861 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4521. Min Act: -0.0000

Data Index: 589890 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1050377 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4714. Min Act: -0.0000

Data Index: 355855 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4388. Min Act: -0.0000

Data Index: 263840 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1133157 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1092061 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4372. Min Act: -0.0000

Data Index: 905353 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4275. Min Act: -0.0000

Data Index: 519590 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4223. Min Act: -0.0000

Data Index: 716176 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.4443. Min Act: -0.0000

Data Index: 1150108 (C4 (Web Text))

Max Activating Token Index: 28