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

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

Neuron 2790 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1602. Min Range: -2.1602

Max Act: 2.1602. Min Act: -0.0000

Data Index: 394114 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.8876. Min Act: -0.0000

Data Index: 1162581 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.7919. Min Act: -0.0000

Data Index: 419355 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.5321. Min Act: -0.0000

Data Index: 99715 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.6042. Min Act: -0.0000

Data Index: 576232 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.4218. Min Act: -0.0000

Data Index: 1184835 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.4768. Min Act: -0.0000

Data Index: 1511862 (Python Code)

Max Activating Token Index: 73

Text #7

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.3455. Min Act: -0.0000

Data Index: 776511 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.4566. Min Act: -0.0000

Data Index: 1074301 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.3657. Min Act: -0.0000

Data Index: 1439745 (Python Code)

Max Activating Token Index: 896

Text #10

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.3228. Min Act: -0.0000

Data Index: 1628437 (Python Code)

Max Activating Token Index: 888

Text #11

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.3149. Min Act: -0.0000

Data Index: 1619559 (Python Code)

Max Activating Token Index: 334

Text #12

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.3123. Min Act: -0.0000

Data Index: 311826 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.2721. Min Act: -0.0000

Data Index: 846226 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.3360. Min Act: -0.0000

Data Index: 25211 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.2889. Min Act: -0.0000

Data Index: 1532029 (Python Code)

Max Activating Token Index: 802

Text #16

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.3022. Min Act: -0.0000

Data Index: 199881 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.2618. Min Act: -0.0000

Data Index: 1404600 (Python Code)

Max Activating Token Index: 573

Text #18

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.3628. Min Act: -0.0000

Data Index: 1099336 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 2.1602. Min Range: -2.1602

Max Act: 1.2271. Min Act: -0.0000

Data Index: 82254 (C4 (Web Text))

Max Activating Token Index: 400