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

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

Neuron 692 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.4605. Min Act: -0.0001

Data Index: 1540402 (Python Code)

Max Activating Token Index: 553

Text #1

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.4353. Min Act: -0.0001

Data Index: 1519644 (Python Code)

Max Activating Token Index: 285

Text #2

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3911. Min Act: -0.0001

Data Index: 1136686 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3871. Min Act: -0.0001

Data Index: 755553 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3864. Min Act: -0.0001

Data Index: 814084 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3747. Min Act: -0.0001

Data Index: 117535 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3889. Min Act: -0.0001

Data Index: 13252 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3679. Min Act: -0.0001

Data Index: 421945 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3805. Min Act: -0.0001

Data Index: 672227 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3760. Min Act: -0.0001

Data Index: 443764 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3694. Min Act: -0.0001

Data Index: 1618111 (Python Code)

Max Activating Token Index: 225

Text #11

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3383. Min Act: -0.0001

Data Index: 770743 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3207. Min Act: -0.0001

Data Index: 1131703 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3849. Min Act: -0.0001

Data Index: 206215 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3826. Min Act: -0.0001

Data Index: 520930 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3661. Min Act: -0.0001

Data Index: 828050 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3463. Min Act: -0.0001

Data Index: 234343 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3752. Min Act: -0.0001

Data Index: 899340 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3328. Min Act: -0.0001

Data Index: 1160617 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.4605. Min Range: -0.4605

Max Act: 0.3507. Min Act: -0.0001

Data Index: 15438 (C4 (Web Text))

Max Activating Token Index: 492