Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1855 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.7674. Min Act: -0.0000

Data Index: 610074 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6500. Min Act: -0.0000

Data Index: 742290 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6226. Min Act: -0.0001

Data Index: 161110 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.6351. Min Act: -0.0000

Data Index: 884483 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5857. Min Act: -0.0000

Data Index: 921515 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1219742 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5721. Min Act: -0.0000

Data Index: 947422 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5639. Min Act: -0.0000

Data Index: 900384 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1123062 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5542. Min Act: -0.0001

Data Index: 946968 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5239. Min Act: -0.0000

Data Index: 188486 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5269. Min Act: -0.0001

Data Index: 401237 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5093. Min Act: -0.0000

Data Index: 577628 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5353. Min Act: -0.0001

Data Index: 277780 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1054974 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.4943. Min Act: -0.0000

Data Index: 1063400 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.4891. Min Act: -0.0000

Data Index: 150053 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.4989. Min Act: -0.0000

Data Index: 394618 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.4978. Min Act: -0.0000

Data Index: 428971 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.7674. Min Range: -0.7674

Max Act: 0.4824. Min Act: -0.0000

Data Index: 897306 (C4 (Web Text))

Max Activating Token Index: 812