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

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

Neuron 829 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.2054. Min Act: -0.0000

Data Index: 643144 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1923. Min Act: -0.0000

Data Index: 118370 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1675. Min Act: -0.0000

Data Index: 236469 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1823. Min Act: -0.0000

Data Index: 957084 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1810. Min Act: -0.0000

Data Index: 156220 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1797. Min Act: -0.0000

Data Index: 50910 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1579. Min Act: -0.0000

Data Index: 1092079 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1562. Min Act: -0.0000

Data Index: 1173974 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1602. Min Act: -0.0000

Data Index: 1272656 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1530. Min Act: -0.0000

Data Index: 763709 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1472. Min Act: -0.0000

Data Index: 253913 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1559. Min Act: -0.0000

Data Index: 978069 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1494. Min Act: -0.0000

Data Index: 986928 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1488. Min Act: -0.0000

Data Index: 686068 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1204905 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1436. Min Act: -0.0000

Data Index: 131376 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1367. Min Act: -0.0000

Data Index: 13757 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1420. Min Act: -0.0000

Data Index: 911164 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1362. Min Act: -0.0000

Data Index: 43444 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1287. Min Act: -0.0000

Data Index: 996385 (C4 (Web Text))

Max Activating Token Index: 601