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

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

Neuron 497 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: 8.4942. Min Range: -8.4942

Max Act: 8.2558. Min Act: -0.0000

Data Index: 481982 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 8.4942. Min Range: -8.4942

Max Act: 8.0367. Min Act: -0.0000

Data Index: 1076571 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 8.4942. Min Range: -8.4942

Max Act: 8.4942. Min Act: -0.0000

Data Index: 193671 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 8.4942. Min Range: -8.4942

Max Act: 8.2117. Min Act: -0.0000

Data Index: 847925 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 8.4942. Min Range: -8.4942

Max Act: 7.6002. Min Act: -0.0000

Data Index: 47799 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 8.4942. Min Range: -8.4942

Max Act: 7.7102. Min Act: -0.0000

Data Index: 566188 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 8.4942. Min Range: -8.4942

Max Act: 7.5761. Min Act: -0.0000

Data Index: 50987 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 8.4942. Min Range: -8.4942

Max Act: 6.9025. Min Act: -0.0000

Data Index: 626586 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 8.4942. Min Range: -8.4942

Max Act: 6.8230. Min Act: -0.0000

Data Index: 1308859 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 8.4942. Min Range: -8.4942

Max Act: 6.7555. Min Act: -0.0000

Data Index: 500132 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 8.4942. Min Range: -8.4942

Max Act: 6.6218. Min Act: -0.0000

Data Index: 905090 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 8.4942. Min Range: -8.4942

Max Act: 6.7859. Min Act: -0.0000

Data Index: 1146753 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 8.4942. Min Range: -8.4942

Max Act: 6.4847. Min Act: -0.0000

Data Index: 2303 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 8.4942. Min Range: -8.4942

Max Act: 6.4546. Min Act: -0.0000

Data Index: 444413 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 8.4942. Min Range: -8.4942

Max Act: 6.2573. Min Act: -0.0000

Data Index: 1310333 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 8.4942. Min Range: -8.4942

Max Act: 6.2189. Min Act: -0.0000

Data Index: 987880 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 8.4942. Min Range: -8.4942

Max Act: 6.1764. Min Act: -0.0000

Data Index: 830295 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 8.4942. Min Range: -8.4942

Max Act: 5.6121. Min Act: -0.0000

Data Index: 1116695 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 8.4942. Min Range: -8.4942

Max Act: 5.9625. Min Act: -0.0000

Data Index: 475955 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 8.4942. Min Range: -8.4942

Max Act: 5.8981. Min Act: -0.0000

Data Index: 482527 (C4 (Web Text))

Max Activating Token Index: 389