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

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

Neuron 3990 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3149. Min Range: -3.3149

Max Act: 3.3149. Min Act: -0.0000

Data Index: 305334 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 3.3149. Min Range: -3.3149

Max Act: 3.1174. Min Act: -0.0000

Data Index: 1157590 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 3.3149. Min Range: -3.3149

Max Act: 2.8626. Min Act: -0.0000

Data Index: 271091 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 3.3149. Min Range: -3.3149

Max Act: 3.0540. Min Act: -0.0000

Data Index: 433865 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 3.3149. Min Range: -3.3149

Max Act: 2.9475. Min Act: -0.0000

Data Index: 535360 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 3.3149. Min Range: -3.3149

Max Act: 2.9442. Min Act: -0.0000

Data Index: 1119249 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 3.3149. Min Range: -3.3149

Max Act: 2.8748. Min Act: -0.0000

Data Index: 70816 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 3.3149. Min Range: -3.3149

Max Act: 2.5164. Min Act: -0.0000

Data Index: 843315 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 3.3149. Min Range: -3.3149

Max Act: 2.7897. Min Act: -0.0000

Data Index: 784952 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 3.3149. Min Range: -3.3149

Max Act: 2.7104. Min Act: -0.0000

Data Index: 1061639 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 3.3149. Min Range: -3.3149

Max Act: 2.6020. Min Act: -0.0000

Data Index: 189689 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 3.3149. Min Range: -3.3149

Max Act: 2.5722. Min Act: -0.0000

Data Index: 312273 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 3.3149. Min Range: -3.3149

Max Act: 2.5386. Min Act: -0.0000

Data Index: 1258729 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 3.3149. Min Range: -3.3149

Max Act: 2.5406. Min Act: -0.0000

Data Index: 1025121 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 3.3149. Min Range: -3.3149

Max Act: 2.3974. Min Act: -0.0000

Data Index: 215106 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 3.3149. Min Range: -3.3149

Max Act: 2.3412. Min Act: -0.0000

Data Index: 619579 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 3.3149. Min Range: -3.3149

Max Act: 2.4619. Min Act: -0.0000

Data Index: 1113275 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 3.3149. Min Range: -3.3149

Max Act: 2.4554. Min Act: -0.0000

Data Index: 1198359 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 3.3149. Min Range: -3.3149

Max Act: 2.4495. Min Act: -0.0000

Data Index: 2126 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 3.3149. Min Range: -3.3149

Max Act: 2.4377. Min Act: -0.0000

Data Index: 116830 (C4 (Web Text))

Max Activating Token Index: 4