Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2396 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1689. Min Act: -0.0000

Data Index: 768434 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1458. Min Act: -0.0000

Data Index: 616464 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1590. Min Act: -0.0000

Data Index: 163182 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1072835 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1410. Min Act: -0.0000

Data Index: 978368 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1197. Min Act: -0.0001

Data Index: 925854 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1338. Min Act: -0.0000

Data Index: 367457 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1141234 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1282. Min Act: -0.0001

Data Index: 1329297 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1269. Min Act: -0.0000

Data Index: 497894 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1091. Min Act: -0.0000

Data Index: 214252 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1246. Min Act: -0.0001

Data Index: 346567 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1163. Min Act: -0.0001

Data Index: 955316 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1149. Min Act: -0.0000

Data Index: 1345705 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1101. Min Act: -0.0000

Data Index: 488623 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1061. Min Act: -0.0001

Data Index: 80165 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.0915. Min Act: -0.0001

Data Index: 620278 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1081059 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.1046. Min Act: -0.0001

Data Index: 954067 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.1689. Min Range: -0.1689

Max Act: 0.0907. Min Act: -0.0001

Data Index: 770662 (C4 (Web Text))

Max Activating Token Index: 861