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

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

Neuron 91 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2103. Min Range: -2.2103

Max Act: 2.2103. Min Act: -0.0000

Data Index: 972339 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 2.2103. Min Range: -2.2103

Max Act: 2.1304. Min Act: -0.0000

Data Index: 175375 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 2.2103. Min Range: -2.2103

Max Act: 2.0822. Min Act: -0.0000

Data Index: 131229 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 2.2103. Min Range: -2.2103

Max Act: 2.0679. Min Act: -0.0000

Data Index: 434053 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.9980. Min Act: -0.0000

Data Index: 584938 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 2.2103. Min Range: -2.2103

Max Act: 2.0177. Min Act: -0.0000

Data Index: 576504 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 2.2103. Min Range: -2.2103

Max Act: 2.0151. Min Act: -0.0000

Data Index: 1172399 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.9887. Min Act: -0.0000

Data Index: 835288 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.8817. Min Act: -0.0000

Data Index: 129426 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 2.2103. Min Range: -2.2103

Max Act: 2.0004. Min Act: -0.0000

Data Index: 398281 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.9589. Min Act: -0.0000

Data Index: 131587 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.9418. Min Act: -0.0000

Data Index: 530580 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.8898. Min Act: -0.0000

Data Index: 481074 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.9446. Min Act: -0.0000

Data Index: 1355680 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.8951. Min Act: -0.0000

Data Index: 939675 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.9050. Min Act: -0.0000

Data Index: 588299 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.7980. Min Act: -0.0000

Data Index: 1315401 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.8933. Min Act: -0.0000

Data Index: 604847 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.8689. Min Act: -0.0000

Data Index: 943407 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 2.2103. Min Range: -2.2103

Max Act: 1.8630. Min Act: -0.0000

Data Index: 1260114 (C4 (Web Text))

Max Activating Token Index: 429