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

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

Neuron 5347 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: 6.7798. Min Range: -6.7798

Max Act: 6.7798. Min Act: -0.0000

Data Index: 140405 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 6.7798. Min Range: -6.7798

Max Act: 4.7925. Min Act: -0.0000

Data Index: 40165 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 6.7798. Min Range: -6.7798

Max Act: 3.8601. Min Act: -0.0000

Data Index: 816432 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 6.7798. Min Range: -6.7798

Max Act: 3.8328. Min Act: -0.0000

Data Index: 1408075 (Python Code)

Max Activating Token Index: 74

Text #4

Max Range: 6.7798. Min Range: -6.7798

Max Act: 3.4508. Min Act: -0.0000

Data Index: 1248354 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 6.7798. Min Range: -6.7798

Max Act: 3.9068. Min Act: -0.0000

Data Index: 137479 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 6.7798. Min Range: -6.7798

Max Act: 3.7279. Min Act: -0.0000

Data Index: 1218812 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 6.7798. Min Range: -6.7798

Max Act: 3.5363. Min Act: -0.0000

Data Index: 1308803 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 6.7798. Min Range: -6.7798

Max Act: 3.8470. Min Act: -0.0000

Data Index: 477465 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 6.7798. Min Range: -6.7798

Max Act: 3.5681. Min Act: -0.0000

Data Index: 1338500 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 6.7798. Min Range: -6.7798

Max Act: 3.3584. Min Act: -0.0000

Data Index: 356776 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 6.7798. Min Range: -6.7798

Max Act: 3.5086. Min Act: -0.0000

Data Index: 1036618 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 6.7798. Min Range: -6.7798

Max Act: 3.6507. Min Act: -0.0000

Data Index: 279205 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 6.7798. Min Range: -6.7798

Max Act: 3.3019. Min Act: -0.0000

Data Index: 642147 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 6.7798. Min Range: -6.7798

Max Act: 3.4550. Min Act: -0.0000

Data Index: 397043 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 6.7798. Min Range: -6.7798

Max Act: 3.3059. Min Act: -0.0000

Data Index: 133419 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 6.7798. Min Range: -6.7798

Max Act: 3.2589. Min Act: -0.0000

Data Index: 472290 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 6.7798. Min Range: -6.7798

Max Act: 3.4380. Min Act: -0.0000

Data Index: 262303 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 6.7798. Min Range: -6.7798

Max Act: 3.2710. Min Act: -0.0000

Data Index: 524108 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 6.7798. Min Range: -6.7798

Max Act: 3.3754. Min Act: -0.0000

Data Index: 738313 (C4 (Web Text))

Max Activating Token Index: 768