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

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

Neuron 1376 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: 1.6963. Min Range: -1.6963

Max Act: 1.6963. Min Act: -0.0000

Data Index: 990464 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.5791. Min Act: -0.0000

Data Index: 1020502 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.5283. Min Act: -0.0000

Data Index: 311021 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4771. Min Act: -0.0000

Data Index: 139702 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4913. Min Act: -0.0000

Data Index: 944798 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4746. Min Act: -0.0000

Data Index: 1020067 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4573. Min Act: -0.0000

Data Index: 767696 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4547. Min Act: -0.0000

Data Index: 468455 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4443. Min Act: -0.0000

Data Index: 365007 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4374. Min Act: -0.0000

Data Index: 1041888 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.5205. Min Act: -0.0000

Data Index: 147573 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4394. Min Act: -0.0000

Data Index: 531781 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4216. Min Act: -0.0000

Data Index: 1323596 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4118. Min Act: -0.0000

Data Index: 508147 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4122. Min Act: -0.0000

Data Index: 345288 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4108. Min Act: -0.0000

Data Index: 658582 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.3602. Min Act: -0.0000

Data Index: 758166 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.3855. Min Act: -0.0000

Data Index: 1086319 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.3524. Min Act: -0.0000

Data Index: 62766 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.3766. Min Act: -0.0000

Data Index: 485511 (C4 (Web Text))

Max Activating Token Index: 544