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

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

Neuron 4704 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.8116. Min Act: -0.0000

Data Index: 1326660 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.8284. Min Act: -0.0000

Data Index: 412434 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7537. Min Act: -0.0000

Data Index: 526147 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7467. Min Act: -0.0000

Data Index: 215957 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7630. Min Act: -0.0000

Data Index: 710694 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7324. Min Act: -0.0000

Data Index: 1197821 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6967. Min Act: -0.0000

Data Index: 561622 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6962. Min Act: -0.0000

Data Index: 806477 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6873. Min Act: -0.0000

Data Index: 647143 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7120. Min Act: -0.0000

Data Index: 220120 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7058. Min Act: -0.0000

Data Index: 726522 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7070. Min Act: -0.0000

Data Index: 322382 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1241599 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6968. Min Act: -0.0000

Data Index: 542590 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6673. Min Act: -0.0000

Data Index: 333520 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6618. Min Act: -0.0000

Data Index: 355691 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6580. Min Act: -0.0000

Data Index: 773905 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.7433. Min Act: -0.0000

Data Index: 224973 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6296. Min Act: -0.0000

Data Index: 641787 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6569. Min Act: -0.0000

Data Index: 568433 (C4 (Web Text))

Max Activating Token Index: 785