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

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

Neuron 4187 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.2679. Min Act: -0.0000

Data Index: 706340 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.2088. Min Act: -0.0000

Data Index: 650801 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.2079. Min Act: -0.0000

Data Index: 573146 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1085276 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1965. Min Act: -0.0000

Data Index: 208101 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1850. Min Act: -0.0000

Data Index: 201529 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1874. Min Act: -0.0000

Data Index: 222545 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1858. Min Act: -0.0000

Data Index: 1278266 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1864. Min Act: -0.0000

Data Index: 72140 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1714. Min Act: -0.0000

Data Index: 1330928 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1725. Min Act: -0.0000

Data Index: 679423 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1620. Min Act: -0.0000

Data Index: 897724 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1651. Min Act: -0.0000

Data Index: 291078 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1630. Min Act: -0.0000

Data Index: 855240 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1672. Min Act: -0.0000

Data Index: 1121923 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1562. Min Act: -0.0000

Data Index: 746766 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1595. Min Act: -0.0000

Data Index: 890042 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1490. Min Act: -0.0000

Data Index: 1015633 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1636. Min Act: -0.0000

Data Index: 802678 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 0.2679. Min Range: -0.2679

Max Act: 0.1526. Min Act: -0.0000

Data Index: 957056 (C4 (Web Text))

Max Activating Token Index: 543