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

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

Neuron 2248 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: 0.3115. Min Range: -0.3115

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1343091 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2882. Min Act: -0.0000

Data Index: 828654 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2873. Min Act: -0.0000

Data Index: 1324814 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2762. Min Act: -0.0000

Data Index: 385910 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2637. Min Act: -0.0000

Data Index: 199306 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2531. Min Act: -0.0000

Data Index: 729355 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2579. Min Act: -0.0000

Data Index: 647776 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2592. Min Act: -0.0000

Data Index: 338289 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2388. Min Act: -0.0000

Data Index: 1266142 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2380. Min Act: -0.0000

Data Index: 196090 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1316280 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2257. Min Act: -0.0000

Data Index: 235074 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2230. Min Act: -0.0000

Data Index: 538723 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2223. Min Act: -0.0000

Data Index: 974439 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2219. Min Act: -0.0000

Data Index: 410713 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1290957 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2356. Min Act: -0.0000

Data Index: 725899 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1211693 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2274. Min Act: -0.0000

Data Index: 929006 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1123921 (C4 (Web Text))

Max Activating Token Index: 465