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

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

Neuron 2074 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8173. Min Range: -3.8173

Max Act: 3.7364. Min Act: -0.0000

Data Index: 693160 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 3.8173. Min Range: -3.8173

Max Act: 3.8173. Min Act: -0.0000

Data Index: 1610539 (Python Code)

Max Activating Token Index: 517

Text #2

Max Range: 3.8173. Min Range: -3.8173

Max Act: 3.7020. Min Act: -0.0000

Data Index: 627076 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 3.8173. Min Range: -3.8173

Max Act: 2.5461. Min Act: -0.0000

Data Index: 622579 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 3.8173. Min Range: -3.8173

Max Act: 3.3622. Min Act: -0.0000

Data Index: 751083 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 3.8173. Min Range: -3.8173

Max Act: 2.2826. Min Act: -0.0000

Data Index: 18392 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 3.8173. Min Range: -3.8173

Max Act: 2.3370. Min Act: -0.0000

Data Index: 1354891 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 3.8173. Min Range: -3.8173

Max Act: 2.5327. Min Act: -0.0000

Data Index: 265110 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 3.8173. Min Range: -3.8173

Max Act: 1.9279. Min Act: -0.0000

Data Index: 552729 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 3.8173. Min Range: -3.8173

Max Act: 2.3490. Min Act: -0.0000

Data Index: 597797 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 3.8173. Min Range: -3.8173

Max Act: 2.1128. Min Act: -0.0000

Data Index: 210328 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 3.8173. Min Range: -3.8173

Max Act: 2.3112. Min Act: -0.0000

Data Index: 396665 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 3.8173. Min Range: -3.8173

Max Act: 1.8071. Min Act: -0.0000

Data Index: 1643012 (Python Code)

Max Activating Token Index: 751

Text #13

Max Range: 3.8173. Min Range: -3.8173

Max Act: 1.6628. Min Act: -0.0000

Data Index: 125096 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 3.8173. Min Range: -3.8173

Max Act: 1.8444. Min Act: -0.0000

Data Index: 762398 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 3.8173. Min Range: -3.8173

Max Act: 2.0347. Min Act: -0.0000

Data Index: 766328 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 3.8173. Min Range: -3.8173

Max Act: 1.5257. Min Act: -0.0000

Data Index: 1503163 (Python Code)

Max Activating Token Index: 988

Text #17

Max Range: 3.8173. Min Range: -3.8173

Max Act: 1.7380. Min Act: -0.0000

Data Index: 822425 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 3.8173. Min Range: -3.8173

Max Act: 1.7321. Min Act: -0.0000

Data Index: 1281282 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 3.8173. Min Range: -3.8173

Max Act: 1.7698. Min Act: -0.0000

Data Index: 1449576 (Python Code)

Max Activating Token Index: 519