Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1327 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.7954. Min Act: -0.0000

Data Index: 1205670 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1545499 (Python Code)

Max Activating Token Index: 28

Text #2

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.7359. Min Act: -0.0000

Data Index: 1416067 (Python Code)

Max Activating Token Index: 118

Text #3

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1394385 (Python Code)

Max Activating Token Index: 30

Text #4

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6327. Min Act: 0.0001

Data Index: 1360001 (Python Code)

Max Activating Token Index: 47

Text #5

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6149. Min Act: -0.0000

Data Index: 480420 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6043. Min Act: 0.0000

Data Index: 1480233 (Python Code)

Max Activating Token Index: 13

Text #7

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6243. Min Act: 0.0001

Data Index: 1619687 (Python Code)

Max Activating Token Index: 86

Text #8

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1491892 (Python Code)

Max Activating Token Index: 689

Text #9

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6066. Min Act: -0.0000

Data Index: 793235 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5752. Min Act: -0.0000

Data Index: 285112 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1389561 (Python Code)

Max Activating Token Index: 910

Text #12

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1295153 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1425214 (Python Code)

Max Activating Token Index: 848

Text #14

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5570. Min Act: -0.0000

Data Index: 672644 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5442. Min Act: -0.0000

Data Index: 1393055 (Python Code)

Max Activating Token Index: 196

Text #16

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5724. Min Act: 0.0001

Data Index: 542553 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5512. Min Act: -0.0000

Data Index: 1479571 (Python Code)

Max Activating Token Index: 317

Text #18

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5877. Min Act: -0.0000

Data Index: 297274 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1109037 (C4 (Web Text))

Max Activating Token Index: 967