Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5192 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.0339. Min Range: -5.0339

Max Act: 4.9649. Min Act: -0.0000

Data Index: 755160 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 5.0339. Min Range: -5.0339

Max Act: 5.0339. Min Act: -0.0000

Data Index: 1184540 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 5.0339. Min Range: -5.0339

Max Act: 4.3657. Min Act: -0.0000

Data Index: 34719 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 5.0339. Min Range: -5.0339

Max Act: 3.9407. Min Act: -0.0000

Data Index: 319679 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 5.0339. Min Range: -5.0339

Max Act: 4.2665. Min Act: -0.0000

Data Index: 535265 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 5.0339. Min Range: -5.0339

Max Act: 3.5230. Min Act: -0.0000

Data Index: 1170771 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 5.0339. Min Range: -5.0339

Max Act: 4.3165. Min Act: -0.0000

Data Index: 261762 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 5.0339. Min Range: -5.0339

Max Act: 3.8198. Min Act: -0.0000

Data Index: 6847 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 5.0339. Min Range: -5.0339

Max Act: 3.9569. Min Act: -0.0000

Data Index: 1058995 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 5.0339. Min Range: -5.0339

Max Act: 3.5879. Min Act: -0.0000

Data Index: 88571 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 5.0339. Min Range: -5.0339

Max Act: 3.7338. Min Act: -0.0000

Data Index: 460296 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 5.0339. Min Range: -5.0339

Max Act: 3.5484. Min Act: -0.0000

Data Index: 1033523 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 5.0339. Min Range: -5.0339

Max Act: 3.4610. Min Act: -0.0000

Data Index: 623124 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 5.0339. Min Range: -5.0339

Max Act: 3.5720. Min Act: -0.0000

Data Index: 1261279 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 5.0339. Min Range: -5.0339

Max Act: 3.3614. Min Act: -0.0000

Data Index: 208351 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 5.0339. Min Range: -5.0339

Max Act: 3.6927. Min Act: -0.0000

Data Index: 449544 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 5.0339. Min Range: -5.0339

Max Act: 3.6968. Min Act: -0.0000

Data Index: 579065 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 5.0339. Min Range: -5.0339

Max Act: 3.6471. Min Act: -0.0000

Data Index: 477387 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 5.0339. Min Range: -5.0339

Max Act: 3.4331. Min Act: -0.0000

Data Index: 1067329 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 5.0339. Min Range: -5.0339

Max Act: 3.2762. Min Act: -0.0000

Data Index: 609079 (C4 (Web Text))

Max Activating Token Index: 469