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

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

Neuron 5138 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.5887. Min Act: -0.0000

Data Index: 1289371 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 3.5887. Min Range: -3.5887

Max Act: 2.9658. Min Act: -0.0000

Data Index: 201814 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.0509. Min Act: -0.0000

Data Index: 671312 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.2033. Min Act: -0.0000

Data Index: 1269507 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 3.5887. Min Range: -3.5887

Max Act: 2.8396. Min Act: -0.0000

Data Index: 756129 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 3.5887. Min Range: -3.5887

Max Act: 2.9514. Min Act: -0.0000

Data Index: 334024 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.0437. Min Act: -0.0000

Data Index: 1304953 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.0302. Min Act: -0.0000

Data Index: 482025 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 3.5887. Min Range: -3.5887

Max Act: 2.5803. Min Act: -0.0000

Data Index: 208525 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 3.5887. Min Range: -3.5887

Max Act: 2.8378. Min Act: -0.0000

Data Index: 977523 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 3.5887. Min Range: -3.5887

Max Act: 2.8185. Min Act: -0.0000

Data Index: 1184355 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 3.5887. Min Range: -3.5887

Max Act: 2.6775. Min Act: -0.0000

Data Index: 579349 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 3.5887. Min Range: -3.5887

Max Act: 2.6413. Min Act: -0.0000

Data Index: 1177833 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 3.5887. Min Range: -3.5887

Max Act: 2.9065. Min Act: -0.0000

Data Index: 1235929 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 3.5887. Min Range: -3.5887

Max Act: 2.6271. Min Act: -0.0000

Data Index: 521962 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 3.5887. Min Range: -3.5887

Max Act: 2.8830. Min Act: -0.0000

Data Index: 429848 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 3.5887. Min Range: -3.5887

Max Act: 2.5991. Min Act: -0.0000

Data Index: 391924 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 3.5887. Min Range: -3.5887

Max Act: 2.6994. Min Act: -0.0000

Data Index: 1176039 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 3.5887. Min Range: -3.5887

Max Act: 2.6846. Min Act: -0.0000

Data Index: 802652 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 3.5887. Min Range: -3.5887

Max Act: 2.3161. Min Act: -0.0000

Data Index: 1222152 (C4 (Web Text))

Max Activating Token Index: 795