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

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

Neuron 2582 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.7882. Min Act: -0.0000

Data Index: 1160127 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6750. Min Act: -0.0000

Data Index: 1309765 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6257. Min Act: -0.0000

Data Index: 1231864 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.7183. Min Act: -0.0000

Data Index: 1144810 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.3875. Min Act: -0.0000

Data Index: 1313850 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.4919. Min Act: -0.0000

Data Index: 816015 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.3482. Min Act: -0.0000

Data Index: 1178078 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.5985. Min Act: -0.0000

Data Index: 42129 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.4168. Min Act: -0.0000

Data Index: 96207 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.2298. Min Act: -0.0000

Data Index: 268231 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6891. Min Act: -0.0000

Data Index: 1088851 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.2546. Min Act: -0.0000

Data Index: 885001 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.1042. Min Act: -0.0000

Data Index: 99430 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.1951. Min Act: -0.0000

Data Index: 167234 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.1436. Min Act: -0.0000

Data Index: 1536817 (Python Code)

Max Activating Token Index: 210

Text #15

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.1083. Min Act: -0.0000

Data Index: 687777 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.1680. Min Act: -0.0000

Data Index: 1185118 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.0235. Min Act: -0.0000

Data Index: 994308 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 3.7882. Min Range: -3.7882

Max Act: 2.8406. Min Act: -0.0000

Data Index: 325574 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 3.7882. Min Range: -3.7882

Max Act: 2.9710. Min Act: -0.0000

Data Index: 664297 (C4 (Web Text))

Max Activating Token Index: 218