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

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

Neuron 2111 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.3631. Min Act: -0.0000

Data Index: 754231 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1222242 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2671. Min Act: -0.0000

Data Index: 743861 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2707. Min Act: -0.0000

Data Index: 587496 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2525. Min Act: -0.0000

Data Index: 529904 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1012407 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2219. Min Act: -0.0000

Data Index: 949884 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2254. Min Act: -0.0000

Data Index: 2678 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2084. Min Act: -0.0000

Data Index: 237951 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1094753 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2058. Min Act: -0.0000

Data Index: 187363 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2023. Min Act: -0.0000

Data Index: 419907 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2026. Min Act: -0.0000

Data Index: 235791 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.1930. Min Act: -0.0000

Data Index: 952950 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1239451 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.1946. Min Act: -0.0000

Data Index: 543350 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.1932. Min Act: -0.0000

Data Index: 212959 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1194513 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.1912. Min Act: -0.0000

Data Index: 30540 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.1905. Min Act: -0.0000

Data Index: 521867 (C4 (Web Text))

Max Activating Token Index: 820