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

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

Neuron 2334 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: 0.4458. Min Range: -0.4458

Max Act: 0.4458. Min Act: -0.0000

Data Index: 929783 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.4221. Min Act: -0.0000

Data Index: 768280 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.4076. Min Act: -0.0000

Data Index: 25107 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.4111. Min Act: -0.0000

Data Index: 283698 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.4060. Min Act: -0.0001

Data Index: 181674 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3753. Min Act: -0.0000

Data Index: 857820 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3681. Min Act: -0.0000

Data Index: 466978 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3558. Min Act: -0.0001

Data Index: 1286557 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3384. Min Act: -0.0001

Data Index: 973259 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3415. Min Act: -0.0000

Data Index: 974932 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3393. Min Act: -0.0001

Data Index: 224181 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1277327 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3140. Min Act: -0.0000

Data Index: 350771 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3143. Min Act: -0.0001

Data Index: 1126448 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3255. Min Act: -0.0001

Data Index: 1354010 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1130643 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3188. Min Act: -0.0000

Data Index: 123819 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3180. Min Act: -0.0001

Data Index: 689722 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3090. Min Act: -0.0000

Data Index: 926796 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 0.4458. Min Range: -0.4458

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1181100 (C4 (Web Text))

Max Activating Token Index: 128