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

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

Neuron 3628 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: 2.7129. Min Range: -2.7129

Max Act: 2.7129. Min Act: -0.0000

Data Index: 1193900 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 2.7129. Min Range: -2.7129

Max Act: 2.6954. Min Act: -0.0000

Data Index: 109569 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 2.7129. Min Range: -2.7129

Max Act: 2.5754. Min Act: -0.0000

Data Index: 498908 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 2.7129. Min Range: -2.7129

Max Act: 2.4364. Min Act: -0.0000

Data Index: 1106671 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 2.7129. Min Range: -2.7129

Max Act: 2.2428. Min Act: -0.0000

Data Index: 926222 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 2.7129. Min Range: -2.7129

Max Act: 2.3663. Min Act: -0.0000

Data Index: 986360 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 2.7129. Min Range: -2.7129

Max Act: 2.1806. Min Act: -0.0000

Data Index: 1612378 (Python Code)

Max Activating Token Index: 384

Text #7

Max Range: 2.7129. Min Range: -2.7129

Max Act: 2.0722. Min Act: -0.0000

Data Index: 437798 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 2.7129. Min Range: -2.7129

Max Act: 2.1625. Min Act: -0.0000

Data Index: 636370 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 2.7129. Min Range: -2.7129

Max Act: 1.8263. Min Act: -0.0000

Data Index: 812729 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 2.7129. Min Range: -2.7129

Max Act: 1.8796. Min Act: -0.0000

Data Index: 474066 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 2.7129. Min Range: -2.7129

Max Act: 1.8792. Min Act: -0.0000

Data Index: 1253069 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 2.7129. Min Range: -2.7129

Max Act: 1.9736. Min Act: -0.0000

Data Index: 1128973 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 2.7129. Min Range: -2.7129

Max Act: 1.7907. Min Act: -0.0000

Data Index: 813291 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 2.7129. Min Range: -2.7129

Max Act: 1.7888. Min Act: -0.0000

Data Index: 114831 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 2.7129. Min Range: -2.7129

Max Act: 1.6654. Min Act: -0.0000

Data Index: 934877 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 2.7129. Min Range: -2.7129

Max Act: 1.6745. Min Act: -0.0000

Data Index: 1387256 (Python Code)

Max Activating Token Index: 417

Text #17

Max Range: 2.7129. Min Range: -2.7129

Max Act: 1.7507. Min Act: -0.0000

Data Index: 258677 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 2.7129. Min Range: -2.7129

Max Act: 1.7404. Min Act: -0.0000

Data Index: 365548 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 2.7129. Min Range: -2.7129

Max Act: 1.6988. Min Act: -0.0000

Data Index: 448628 (C4 (Web Text))

Max Activating Token Index: 632