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

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

Neuron 2321 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.9635. Min Act: -0.0000

Data Index: 1630942 (Python Code)

Max Activating Token Index: 703

Text #1

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.9652. Min Act: -0.0000

Data Index: 653444 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.7137. Min Act: -0.0000

Data Index: 1447724 (Python Code)

Max Activating Token Index: 672

Text #3

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.6689. Min Act: -0.0000

Data Index: 941961 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.6006. Min Act: -0.0000

Data Index: 1433855 (Python Code)

Max Activating Token Index: 537

Text #5

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.4941. Min Act: -0.0000

Data Index: 1418471 (Python Code)

Max Activating Token Index: 517

Text #6

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.5287. Min Act: -0.0000

Data Index: 1263080 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.5394. Min Act: -0.0000

Data Index: 1457793 (Python Code)

Max Activating Token Index: 877

Text #8

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.4704. Min Act: -0.0000

Data Index: 1540722 (Python Code)

Max Activating Token Index: 224

Text #9

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.4169. Min Act: -0.0000

Data Index: 363529 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.3354. Min Act: -0.0000

Data Index: 1611771 (Python Code)

Max Activating Token Index: 372

Text #11

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.4891. Min Act: -0.0000

Data Index: 1425347 (Python Code)

Max Activating Token Index: 1022

Text #12

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.3532. Min Act: -0.0000

Data Index: 16251 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.3312. Min Act: -0.0000

Data Index: 1561933 (Python Code)

Max Activating Token Index: 365

Text #14

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.2229. Min Act: -0.0000

Data Index: 1372892 (Python Code)

Max Activating Token Index: 311

Text #15

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.2987. Min Act: -0.0000

Data Index: 1536885 (Python Code)

Max Activating Token Index: 160

Text #16

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.2768. Min Act: -0.0000

Data Index: 1510215 (Python Code)

Max Activating Token Index: 546

Text #17

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.2763. Min Act: -0.0000

Data Index: 1471792 (Python Code)

Max Activating Token Index: 173

Text #18

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.2458. Min Act: -0.0000

Data Index: 1365617 (Python Code)

Max Activating Token Index: 201

Text #19

Max Range: 1.9652. Min Range: -1.9652

Max Act: 1.0796. Min Act: -0.0000

Data Index: 925044 (C4 (Web Text))

Max Activating Token Index: 330