Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2772 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1334. Min Act: -0.0001

Data Index: 1201702 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1211. Min Act: -0.0000

Data Index: 971178 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1174. Min Act: -0.0001

Data Index: 889819 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1147. Min Act: -0.0001

Data Index: 176955 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1092. Min Act: -0.0001

Data Index: 513413 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1128. Min Act: -0.0001

Data Index: 417937 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1141. Min Act: -0.0001

Data Index: 723278 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1056. Min Act: -0.0001

Data Index: 868987 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1029. Min Act: -0.0001

Data Index: 470718 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1034. Min Act: -0.0001

Data Index: 543738 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0977. Min Act: -0.0001

Data Index: 719323 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0929. Min Act: -0.0001

Data Index: 751679 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0960. Min Act: -0.0001

Data Index: 378846 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0966. Min Act: -0.0001

Data Index: 968763 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1246941 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0917. Min Act: -0.0001

Data Index: 405501 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0910. Min Act: -0.0001

Data Index: 189795 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0895. Min Act: -0.0001

Data Index: 249802 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0929. Min Act: -0.0001

Data Index: 158284 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0827. Min Act: -0.0001

Data Index: 1106536 (C4 (Web Text))

Max Activating Token Index: 854