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

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

Neuron 85 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: 2.3084. Min Range: -2.3084

Max Act: 2.3084. Min Act: -0.0000

Data Index: 1078078 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 2.3084. Min Range: -2.3084

Max Act: 2.0693. Min Act: -0.0000

Data Index: 374383 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 2.3084. Min Range: -2.3084

Max Act: 1.5951. Min Act: -0.0000

Data Index: 1262777 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 2.3084. Min Range: -2.3084

Max Act: 1.6610. Min Act: -0.0000

Data Index: 980877 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 2.3084. Min Range: -2.3084

Max Act: 1.4559. Min Act: -0.0000

Data Index: 834130 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 2.3084. Min Range: -2.3084

Max Act: 1.3377. Min Act: -0.0000

Data Index: 920382 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 2.3084. Min Range: -2.3084

Max Act: 1.3189. Min Act: -0.0000

Data Index: 530856 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 2.3084. Min Range: -2.3084

Max Act: 1.2289. Min Act: -0.0000

Data Index: 838869 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 2.3084. Min Range: -2.3084

Max Act: 1.2979. Min Act: -0.0000

Data Index: 65240 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 2.3084. Min Range: -2.3084

Max Act: 1.2785. Min Act: -0.0000

Data Index: 491586 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 2.3084. Min Range: -2.3084

Max Act: 1.2639. Min Act: -0.0000

Data Index: 377859 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 2.3084. Min Range: -2.3084

Max Act: 1.1607. Min Act: -0.0000

Data Index: 835461 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 2.3084. Min Range: -2.3084

Max Act: 1.2259. Min Act: -0.0000

Data Index: 654215 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 2.3084. Min Range: -2.3084

Max Act: 1.1421. Min Act: -0.0000

Data Index: 76688 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 2.3084. Min Range: -2.3084

Max Act: 1.2936. Min Act: -0.0000

Data Index: 857518 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 2.3084. Min Range: -2.3084

Max Act: 1.1775. Min Act: -0.0000

Data Index: 313581 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 2.3084. Min Range: -2.3084

Max Act: 1.1647. Min Act: -0.0000

Data Index: 645016 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 2.3084. Min Range: -2.3084

Max Act: 1.1680. Min Act: -0.0000

Data Index: 297208 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 2.3084. Min Range: -2.3084

Max Act: 1.1622. Min Act: -0.0000

Data Index: 1263574 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 2.3084. Min Range: -2.3084

Max Act: 1.0767. Min Act: -0.0000

Data Index: 218578 (C4 (Web Text))

Max Activating Token Index: 153