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

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

Neuron 1788 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1023483 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3954. Min Act: -0.0000

Data Index: 201056 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3694. Min Act: -0.0000

Data Index: 950090 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.4196. Min Act: -0.0000

Data Index: 945893 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3485. Min Act: -0.0000

Data Index: 1125453 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3350. Min Act: -0.0000

Data Index: 340959 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3306. Min Act: -0.0000

Data Index: 921849 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1059319 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3113. Min Act: -0.0000

Data Index: 618311 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2791. Min Act: -0.0000

Data Index: 507175 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2987. Min Act: -0.0000

Data Index: 1295924 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3070. Min Act: -0.0000

Data Index: 163211 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2679. Min Act: -0.0000

Data Index: 112729 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.3068. Min Act: -0.0000

Data Index: 900167 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2976. Min Act: -0.0000

Data Index: 895045 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1336021 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2299. Min Act: -0.0000

Data Index: 968182 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2317. Min Act: -0.0000

Data Index: 1323755 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1144513 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.4537. Min Range: -0.4537

Max Act: 0.2976. Min Act: -0.0000

Data Index: 679125 (C4 (Web Text))

Max Activating Token Index: 226