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

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

Neuron 1528 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: 3.3757. Min Range: -3.3757

Max Act: 3.3757. Min Act: -0.0000

Data Index: 581773 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 3.3757. Min Range: -3.3757

Max Act: 3.1988. Min Act: -0.0001

Data Index: 44370 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 3.3757. Min Range: -3.3757

Max Act: 3.2531. Min Act: -0.0001

Data Index: 182679 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 3.3757. Min Range: -3.3757

Max Act: 3.1056. Min Act: -0.0001

Data Index: 209335 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 3.3757. Min Range: -3.3757

Max Act: 3.0803. Min Act: -0.0001

Data Index: 186059 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 3.3757. Min Range: -3.3757

Max Act: 3.0220. Min Act: -0.0000

Data Index: 1358271 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 3.3757. Min Range: -3.3757

Max Act: 3.0025. Min Act: -0.0001

Data Index: 159595 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 3.3757. Min Range: -3.3757

Max Act: 2.9974. Min Act: -0.0000

Data Index: 364325 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 3.3757. Min Range: -3.3757

Max Act: 2.8789. Min Act: -0.0001

Data Index: 733711 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 3.3757. Min Range: -3.3757

Max Act: 2.8946. Min Act: -0.0001

Data Index: 1071992 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 3.3757. Min Range: -3.3757

Max Act: 2.8844. Min Act: -0.0000

Data Index: 1345002 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 3.3757. Min Range: -3.3757

Max Act: 2.8553. Min Act: -0.0001

Data Index: 663833 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 3.3757. Min Range: -3.3757

Max Act: 2.8586. Min Act: -0.0000

Data Index: 448152 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 3.3757. Min Range: -3.3757

Max Act: 2.8601. Min Act: -0.0001

Data Index: 754616 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 3.3757. Min Range: -3.3757

Max Act: 2.8238. Min Act: -0.0001

Data Index: 1227608 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 3.3757. Min Range: -3.3757

Max Act: 2.8181. Min Act: -0.0000

Data Index: 566743 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 3.3757. Min Range: -3.3757

Max Act: 2.8043. Min Act: -0.0001

Data Index: 1188269 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 3.3757. Min Range: -3.3757

Max Act: 2.7911. Min Act: -0.0001

Data Index: 287719 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 3.3757. Min Range: -3.3757

Max Act: 2.6546. Min Act: -0.0000

Data Index: 562975 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 3.3757. Min Range: -3.3757

Max Act: 2.7741. Min Act: -0.0001

Data Index: 227807 (C4 (Web Text))

Max Activating Token Index: 503