Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4159 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.7575. Min Act: -0.0001

Data Index: 768122 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.7507. Min Act: -0.0001

Data Index: 362220 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.6661. Min Act: -0.0001

Data Index: 474776 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.5350. Min Act: -0.0001

Data Index: 542801 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.4882. Min Act: -0.0001

Data Index: 1113267 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.5308. Min Act: -0.0001

Data Index: 667115 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.5146. Min Act: -0.0001

Data Index: 792839 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.4322. Min Act: -0.0001

Data Index: 89667 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.4190. Min Act: -0.0001

Data Index: 1319538 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.2618. Min Act: -0.0001

Data Index: 587465 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.5029. Min Act: -0.0001

Data Index: 719701 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.4929. Min Act: -0.0001

Data Index: 984227 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.4204. Min Act: -0.0001

Data Index: 1139545 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.3000. Min Act: -0.0001

Data Index: 1356473 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.5063. Min Act: -0.0001

Data Index: 145383 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.4466. Min Act: -0.0001

Data Index: 298059 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.4533. Min Act: -0.0001

Data Index: 811919 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.4594. Min Act: -0.0001

Data Index: 1197656 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.2792. Min Act: -0.0001

Data Index: 944215 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 1.7575. Min Range: -1.7575

Max Act: 1.4252. Min Act: -0.0001

Data Index: 1254489 (C4 (Web Text))

Max Activating Token Index: 369