Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2193 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2380. Min Act: -0.0003

Data Index: 496349 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2297. Min Act: -0.0003

Data Index: 11439 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2019. Min Act: -0.0003

Data Index: 598954 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2046. Min Act: -0.0003

Data Index: 611074 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1982. Min Act: -0.0003

Data Index: 524540 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1882. Min Act: -0.0003

Data Index: 292767 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2156. Min Act: -0.0003

Data Index: 1307507 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1992. Min Act: -0.0003

Data Index: 762665 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1952. Min Act: -0.0003

Data Index: 246843 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1808. Min Act: -0.0003

Data Index: 54453 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1763. Min Act: -0.0003

Data Index: 368208 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1770. Min Act: -0.0003

Data Index: 235484 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1826. Min Act: -0.0003

Data Index: 533550 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1748. Min Act: -0.0003

Data Index: 1349428 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1734. Min Act: -0.0003

Data Index: 382325 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1729. Min Act: -0.0003

Data Index: 1062131 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1724. Min Act: -0.0003

Data Index: 193521 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1721. Min Act: -0.0003

Data Index: 1320520 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1642. Min Act: -0.0003

Data Index: 1318301 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1776. Min Act: -0.0003

Data Index: 1088425 (C4 (Web Text))

Max Activating Token Index: 369