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

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

Neuron 809 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: 4.1515. Min Range: -4.1515

Max Act: 4.1515. Min Act: -0.0000

Data Index: 221071 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 4.1515. Min Range: -4.1515

Max Act: 3.9115. Min Act: -0.0000

Data Index: 1127626 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 4.1515. Min Range: -4.1515

Max Act: 3.7832. Min Act: -0.0000

Data Index: 112593 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 4.1515. Min Range: -4.1515

Max Act: 3.5203. Min Act: -0.0000

Data Index: 1065036 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 4.1515. Min Range: -4.1515

Max Act: 3.8159. Min Act: -0.0000

Data Index: 515593 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 4.1515. Min Range: -4.1515

Max Act: 3.4674. Min Act: -0.0000

Data Index: 763318 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 4.1515. Min Range: -4.1515

Max Act: 3.6910. Min Act: -0.0000

Data Index: 259043 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 4.1515. Min Range: -4.1515

Max Act: 3.5287. Min Act: -0.0000

Data Index: 1292206 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 4.1515. Min Range: -4.1515

Max Act: 3.4622. Min Act: -0.0000

Data Index: 889109 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 4.1515. Min Range: -4.1515

Max Act: 3.5802. Min Act: -0.0000

Data Index: 1237779 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 4.1515. Min Range: -4.1515

Max Act: 3.5558. Min Act: -0.0000

Data Index: 1201671 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 4.1515. Min Range: -4.1515

Max Act: 3.2595. Min Act: -0.0000

Data Index: 375290 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 4.1515. Min Range: -4.1515

Max Act: 3.5566. Min Act: -0.0000

Data Index: 1085411 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 4.1515. Min Range: -4.1515

Max Act: 3.0805. Min Act: -0.0000

Data Index: 369903 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 4.1515. Min Range: -4.1515

Max Act: 3.3697. Min Act: -0.0000

Data Index: 983949 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 4.1515. Min Range: -4.1515

Max Act: 3.3296. Min Act: -0.0000

Data Index: 409782 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 4.1515. Min Range: -4.1515

Max Act: 3.1879. Min Act: -0.0000

Data Index: 225818 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 4.1515. Min Range: -4.1515

Max Act: 3.0537. Min Act: -0.0000

Data Index: 515375 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 4.1515. Min Range: -4.1515

Max Act: 3.1084. Min Act: -0.0000

Data Index: 1078257 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 4.1515. Min Range: -4.1515

Max Act: 3.1097. Min Act: -0.0000

Data Index: 230602 (C4 (Web Text))

Max Activating Token Index: 349