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

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

Neuron 1029 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: 3.1966. Min Range: -3.1966

Max Act: 3.0470. Min Act: -0.0001

Data Index: 1167040 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 3.1966. Min Range: -3.1966

Max Act: 3.1966. Min Act: -0.0001

Data Index: 1266659 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 3.1966. Min Range: -3.1966

Max Act: 2.7738. Min Act: -0.0001

Data Index: 1105001 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 3.1966. Min Range: -3.1966

Max Act: 2.7926. Min Act: -0.0001

Data Index: 654251 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 3.1966. Min Range: -3.1966

Max Act: 2.8068. Min Act: -0.0001

Data Index: 309429 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 3.1966. Min Range: -3.1966

Max Act: 2.6612. Min Act: -0.0001

Data Index: 778252 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 3.1966. Min Range: -3.1966

Max Act: 3.0544. Min Act: -0.0001

Data Index: 950447 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 3.1966. Min Range: -3.1966

Max Act: 2.9040. Min Act: -0.0001

Data Index: 1059095 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 3.1966. Min Range: -3.1966

Max Act: 2.8765. Min Act: -0.0001

Data Index: 1274801 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 3.1966. Min Range: -3.1966

Max Act: 2.8116. Min Act: -0.0001

Data Index: 987174 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 3.1966. Min Range: -3.1966

Max Act: 2.9496. Min Act: -0.0001

Data Index: 1238430 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 3.1966. Min Range: -3.1966

Max Act: 2.9348. Min Act: -0.0001

Data Index: 904309 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 3.1966. Min Range: -3.1966

Max Act: 2.7833. Min Act: -0.0001

Data Index: 1081795 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 3.1966. Min Range: -3.1966

Max Act: 2.7972. Min Act: -0.0001

Data Index: 647415 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 3.1966. Min Range: -3.1966

Max Act: 2.6632. Min Act: -0.0001

Data Index: 53007 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 3.1966. Min Range: -3.1966

Max Act: 2.6686. Min Act: -0.0001

Data Index: 921894 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 3.1966. Min Range: -3.1966

Max Act: 2.9361. Min Act: -0.0001

Data Index: 373291 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 3.1966. Min Range: -3.1966

Max Act: 2.7931. Min Act: -0.0001

Data Index: 372663 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 3.1966. Min Range: -3.1966

Max Act: 2.9280. Min Act: -0.0001

Data Index: 650955 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 3.1966. Min Range: -3.1966

Max Act: 2.9094. Min Act: -0.0001

Data Index: 804972 (C4 (Web Text))

Max Activating Token Index: 295