Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1925 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.4504. Min Act: -0.0000

Data Index: 1025107 (The Pile)

Max Activating Token Index: 236

Text #1

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3879. Min Act: -0.0000

Data Index: 924135 (The Pile)

Max Activating Token Index: 147

Text #2

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2678. Min Act: -0.0000

Data Index: 697130 (The Pile)

Max Activating Token Index: 147

Text #3

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1594712 (The Pile)

Max Activating Token Index: 251

Text #4

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.1866. Min Act: -0.0000

Data Index: 1889193 (The Pile)

Max Activating Token Index: 154

Text #5

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1510132 (The Pile)

Max Activating Token Index: 209

Text #6

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1219057 (The Pile)

Max Activating Token Index: 201

Text #7

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.1903. Min Act: -0.0000

Data Index: 501397 (The Pile)

Max Activating Token Index: 206

Text #8

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.1917. Min Act: -0.0000

Data Index: 1223749 (The Pile)

Max Activating Token Index: 580

Text #9

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.1555. Min Act: -0.0000

Data Index: 1481364 (The Pile)

Max Activating Token Index: 162

Text #10

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.1662. Min Act: -0.0000

Data Index: 1777851 (The Pile)

Max Activating Token Index: 142

Text #11

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1881058 (The Pile)

Max Activating Token Index: 208

Text #12

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1010338 (The Pile)

Max Activating Token Index: 225

Text #13

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.1618. Min Act: -0.0000

Data Index: 440461 (The Pile)

Max Activating Token Index: 260

Text #14

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.1419. Min Act: -0.0000

Data Index: 1225778 (The Pile)

Max Activating Token Index: 909

Text #15

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.1690. Min Act: -0.0000

Data Index: 1268818 (The Pile)

Max Activating Token Index: 418

Text #16

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.1492. Min Act: -0.0000

Data Index: 849072 (The Pile)

Max Activating Token Index: 369

Text #17

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.1629. Min Act: -0.0000

Data Index: 1426124 (The Pile)

Max Activating Token Index: 726

Text #18

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.1559. Min Act: -0.0000

Data Index: 1925446 (The Pile)

Max Activating Token Index: 197

Text #19

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.1714. Min Act: -0.0000

Data Index: 1552406 (The Pile)

Max Activating Token Index: 526