Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3555 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.6616. Min Range: -2.6616

Max Act: 2.6616. Min Act: -0.0000

Data Index: 224525 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 2.6616. Min Range: -2.6616

Max Act: 2.4273. Min Act: -0.0000

Data Index: 955376 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 2.6616. Min Range: -2.6616

Max Act: 2.0720. Min Act: -0.0000

Data Index: 812541 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 2.6616. Min Range: -2.6616

Max Act: 2.1111. Min Act: -0.0000

Data Index: 637597 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 2.6616. Min Range: -2.6616

Max Act: 2.3628. Min Act: -0.0000

Data Index: 669278 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 2.6616. Min Range: -2.6616

Max Act: 2.3411. Min Act: -0.0000

Data Index: 616881 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 2.6616. Min Range: -2.6616

Max Act: 2.1788. Min Act: -0.0000

Data Index: 141616 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 2.6616. Min Range: -2.6616

Max Act: 2.2399. Min Act: -0.0000

Data Index: 1098648 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 2.6616. Min Range: -2.6616

Max Act: 2.2484. Min Act: -0.0000

Data Index: 240535 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 2.6616. Min Range: -2.6616

Max Act: 2.0356. Min Act: -0.0000

Data Index: 644398 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 2.6616. Min Range: -2.6616

Max Act: 2.4653. Min Act: -0.0000

Data Index: 209360 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 2.6616. Min Range: -2.6616

Max Act: 2.3339. Min Act: -0.0000

Data Index: 545352 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 2.6616. Min Range: -2.6616

Max Act: 2.1829. Min Act: -0.0000

Data Index: 30156 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 2.6616. Min Range: -2.6616

Max Act: 2.1141. Min Act: -0.0000

Data Index: 1008987 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 2.6616. Min Range: -2.6616

Max Act: 1.9053. Min Act: -0.0000

Data Index: 863594 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 2.6616. Min Range: -2.6616

Max Act: 2.1022. Min Act: -0.0000

Data Index: 597388 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 2.6616. Min Range: -2.6616

Max Act: 1.9104. Min Act: -0.0000

Data Index: 323090 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 2.6616. Min Range: -2.6616

Max Act: 1.9140. Min Act: -0.0000

Data Index: 924240 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 2.6616. Min Range: -2.6616

Max Act: 1.9043. Min Act: -0.0000

Data Index: 1241079 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 2.6616. Min Range: -2.6616

Max Act: 1.9996. Min Act: -0.0000

Data Index: 1024688 (C4 (Web Text))

Max Activating Token Index: 175