Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2876 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.4952. Min Act: -0.0000

Data Index: 1267981 (The Pile)

Max Activating Token Index: 561

Text #1

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.4444. Min Act: -0.0000

Data Index: 859183 (The Pile)

Max Activating Token Index: 890

Text #2

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.4384. Min Act: -0.0000

Data Index: 491416 (The Pile)

Max Activating Token Index: 379

Text #3

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.4730. Min Act: -0.0000

Data Index: 1083790 (The Pile)

Max Activating Token Index: 111

Text #4

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.4296. Min Act: -0.0000

Data Index: 807572 (The Pile)

Max Activating Token Index: 782

Text #5

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.3936. Min Act: -0.0000

Data Index: 1883755 (The Pile)

Max Activating Token Index: 363

Text #6

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.3924. Min Act: -0.0000

Data Index: 1453739 (The Pile)

Max Activating Token Index: 30

Text #7

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.3035. Min Act: 0.0000

Data Index: 471652 (The Pile)

Max Activating Token Index: 60

Text #8

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.2960. Min Act: -0.0000

Data Index: 526670 (The Pile)

Max Activating Token Index: 573

Text #9

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.4379. Min Act: -0.0000

Data Index: 1615421 (The Pile)

Max Activating Token Index: 950

Text #10

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.4130. Min Act: -0.0000

Data Index: 1929754 (The Pile)

Max Activating Token Index: 466

Text #11

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.3289. Min Act: -0.0000

Data Index: 650199 (The Pile)

Max Activating Token Index: 282

Text #12

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.2325. Min Act: -0.0000

Data Index: 1387711 (The Pile)

Max Activating Token Index: 899

Text #13

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.3277. Min Act: -0.0000

Data Index: 1020010 (The Pile)

Max Activating Token Index: 902

Text #14

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.2076. Min Act: -0.0000

Data Index: 914827 (The Pile)

Max Activating Token Index: 704

Text #15

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.2860. Min Act: -0.0000

Data Index: 1336676 (The Pile)

Max Activating Token Index: 939

Text #16

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.2889. Min Act: -0.0000

Data Index: 1007378 (The Pile)

Max Activating Token Index: 696

Text #17

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.3148. Min Act: -0.0000

Data Index: 1854189 (The Pile)

Max Activating Token Index: 224

Text #18

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.2023. Min Act: -0.0000

Data Index: 245032 (The Pile)

Max Activating Token Index: 531

Text #19

Max Range: 1.4952. Min Range: -1.4952

Max Act: 1.2480. Min Act: -0.0000

Data Index: 1524249 (The Pile)

Max Activating Token Index: 536