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

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

Neuron 314 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1521. Min Range: -7.1521

Max Act: 7.1521. Min Act: -0.0000

Data Index: 369720 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 7.1521. Min Range: -7.1521

Max Act: 6.5450. Min Act: -0.0000

Data Index: 945047 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 7.1521. Min Range: -7.1521

Max Act: 6.5045. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 7.1521. Min Range: -7.1521

Max Act: 6.4293. Min Act: -0.0000

Data Index: 1106330 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 7.1521. Min Range: -7.1521

Max Act: 6.3216. Min Act: -0.0000

Data Index: 32052 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 7.1521. Min Range: -7.1521

Max Act: 6.0650. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 7.1521. Min Range: -7.1521

Max Act: 6.1304. Min Act: -0.0000

Data Index: 1414266 (Python Code)

Max Activating Token Index: 916

Text #7

Max Range: 7.1521. Min Range: -7.1521

Max Act: 5.8509. Min Act: -0.0000

Data Index: 805170 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 7.1521. Min Range: -7.1521

Max Act: 6.2101. Min Act: -0.0000

Data Index: 44342 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 7.1521. Min Range: -7.1521

Max Act: 6.1411. Min Act: -0.0000

Data Index: 644142 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 7.1521. Min Range: -7.1521

Max Act: 5.9411. Min Act: -0.0000

Data Index: 1600062 (Python Code)

Max Activating Token Index: 372

Text #11

Max Range: 7.1521. Min Range: -7.1521

Max Act: 5.5175. Min Act: -0.0000

Data Index: 815510 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 7.1521. Min Range: -7.1521

Max Act: 5.8456. Min Act: -0.0000

Data Index: 797284 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 7.1521. Min Range: -7.1521

Max Act: 5.4525. Min Act: -0.0000

Data Index: 270870 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 7.1521. Min Range: -7.1521

Max Act: 5.4937. Min Act: -0.0000

Data Index: 859968 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 7.1521. Min Range: -7.1521

Max Act: 5.4391. Min Act: -0.0000

Data Index: 577586 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 7.1521. Min Range: -7.1521

Max Act: 5.1330. Min Act: -0.0000

Data Index: 507132 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 7.1521. Min Range: -7.1521

Max Act: 5.3297. Min Act: -0.0000

Data Index: 407231 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 7.1521. Min Range: -7.1521

Max Act: 4.5705. Min Act: -0.0000

Data Index: 112432 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 7.1521. Min Range: -7.1521

Max Act: 5.2765. Min Act: -0.0000

Data Index: 1419552 (Python Code)

Max Activating Token Index: 340