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

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

Neuron 1114 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: 1.4504. Min Range: -1.4504

Max Act: 1.4504. Min Act: -0.0000

Data Index: 874573 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.2083. Min Act: -0.0000

Data Index: 649200 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.1023. Min Act: -0.0000

Data Index: 390020 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.0117. Min Act: -0.0000

Data Index: 213593 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.0110. Min Act: -0.0000

Data Index: 899665 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.0174. Min Act: -0.0000

Data Index: 432363 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.9450. Min Act: -0.0000

Data Index: 4559 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.9065. Min Act: -0.0000

Data Index: 331102 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.9539. Min Act: -0.0000

Data Index: 139791 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.9409. Min Act: -0.0000

Data Index: 853270 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.9328. Min Act: -0.0000

Data Index: 132933 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.8732. Min Act: -0.0000

Data Index: 746371 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.9146. Min Act: -0.0000

Data Index: 151394 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.9069. Min Act: -0.0000

Data Index: 1319686 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.9676. Min Act: -0.0000

Data Index: 1130246 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.9090. Min Act: -0.0000

Data Index: 868191 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.9072. Min Act: -0.0000

Data Index: 78371 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.8771. Min Act: -0.0000

Data Index: 795053 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.8386. Min Act: -0.0000

Data Index: 118878 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 1.4504. Min Range: -1.4504

Max Act: 0.8964. Min Act: -0.0000

Data Index: 1146949 (C4 (Web Text))

Max Activating Token Index: 246