Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1870 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.4352. Min Act: -0.0002

Data Index: 758452 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.4146. Min Act: -0.0002

Data Index: 942622 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.4053. Min Act: -0.0002

Data Index: 755516 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3955. Min Act: -0.0002

Data Index: 314381 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3975. Min Act: -0.0002

Data Index: 308383 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.4028. Min Act: -0.0002

Data Index: 1308426 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3816. Min Act: -0.0002

Data Index: 207375 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.4100. Min Act: -0.0002

Data Index: 1321384 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3739. Min Act: -0.0002

Data Index: 1171456 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3641. Min Act: -0.0002

Data Index: 476499 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3795. Min Act: -0.0002

Data Index: 1321758 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3792. Min Act: -0.0002

Data Index: 1326725 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3648. Min Act: -0.0002

Data Index: 1221565 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3586. Min Act: -0.0002

Data Index: 1341924 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3753. Min Act: -0.0002

Data Index: 136181 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3542. Min Act: -0.0002

Data Index: 34200 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3418. Min Act: -0.0002

Data Index: 1228563 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3669. Min Act: -0.0002

Data Index: 409040 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3540. Min Act: -0.0002

Data Index: 981562 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.4352. Min Range: -0.4352

Max Act: 0.3524. Min Act: -0.0002

Data Index: 830242 (C4 (Web Text))

Max Activating Token Index: 928