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

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

Neuron 5760 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: 2.0497. Min Range: -2.0497

Max Act: 2.0497. Min Act: -0.0000

Data Index: 484266 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 2.0497. Min Range: -2.0497

Max Act: 1.9317. Min Act: -0.0000

Data Index: 372602 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 2.0497. Min Range: -2.0497

Max Act: 2.0438. Min Act: -0.0000

Data Index: 811260 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 2.0497. Min Range: -2.0497

Max Act: 1.8973. Min Act: -0.0000

Data Index: 779 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 2.0497. Min Range: -2.0497

Max Act: 1.9074. Min Act: -0.0001

Data Index: 1036241 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 2.0497. Min Range: -2.0497

Max Act: 1.8086. Min Act: -0.0000

Data Index: 651088 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 2.0497. Min Range: -2.0497

Max Act: 1.6685. Min Act: -0.0000

Data Index: 842966 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 2.0497. Min Range: -2.0497

Max Act: 1.7254. Min Act: -0.0000

Data Index: 247866 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 2.0497. Min Range: -2.0497

Max Act: 1.6386. Min Act: -0.0000

Data Index: 486621 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 2.0497. Min Range: -2.0497

Max Act: 1.5817. Min Act: -0.0000

Data Index: 206691 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 2.0497. Min Range: -2.0497

Max Act: 1.5669. Min Act: -0.0000

Data Index: 615366 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 2.0497. Min Range: -2.0497

Max Act: 1.4939. Min Act: -0.0000

Data Index: 1174561 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 2.0497. Min Range: -2.0497

Max Act: 1.2962. Min Act: -0.0000

Data Index: 435158 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 2.0497. Min Range: -2.0497

Max Act: 1.1294. Min Act: -0.0000

Data Index: 1352287 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 2.0497. Min Range: -2.0497

Max Act: 1.1742. Min Act: -0.0000

Data Index: 259779 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 2.0497. Min Range: -2.0497

Max Act: 1.1451. Min Act: -0.0000

Data Index: 1298489 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 2.0497. Min Range: -2.0497

Max Act: 1.1386. Min Act: -0.0000

Data Index: 315523 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 2.0497. Min Range: -2.0497

Max Act: 1.0892. Min Act: -0.0001

Data Index: 536048 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 2.0497. Min Range: -2.0497

Max Act: 1.0734. Min Act: -0.0000

Data Index: 347208 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 2.0497. Min Range: -2.0497

Max Act: 1.0292. Min Act: -0.0000

Data Index: 245992 (C4 (Web Text))

Max Activating Token Index: 780