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

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

Neuron 3366 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: 0.9667. Min Range: -0.9667

Max Act: 0.9667. Min Act: -0.0000

Data Index: 11679 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 0.9667. Min Range: -0.9667

Max Act: 0.9661. Min Act: -0.0000

Data Index: 1114709 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.9667. Min Range: -0.9667

Max Act: 0.9162. Min Act: -0.0000

Data Index: 357007 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.9667. Min Range: -0.9667

Max Act: 0.9255. Min Act: -0.0000

Data Index: 87599 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.9667. Min Range: -0.9667

Max Act: 0.8793. Min Act: -0.0000

Data Index: 1297530 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.9667. Min Range: -0.9667

Max Act: 0.8666. Min Act: -0.0000

Data Index: 388778 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.9667. Min Range: -0.9667

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1170134 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.9667. Min Range: -0.9667

Max Act: 0.8869. Min Act: -0.0000

Data Index: 13412 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.9667. Min Range: -0.9667

Max Act: 0.8063. Min Act: -0.0000

Data Index: 54822 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.9667. Min Range: -0.9667

Max Act: 0.8683. Min Act: -0.0000

Data Index: 1257908 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 0.9667. Min Range: -0.9667

Max Act: 0.8009. Min Act: -0.0000

Data Index: 585945 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 0.9667. Min Range: -0.9667

Max Act: 0.7714. Min Act: -0.0000

Data Index: 972201 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.9667. Min Range: -0.9667

Max Act: 0.8113. Min Act: -0.0000

Data Index: 1316240 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.9667. Min Range: -0.9667

Max Act: 0.7503. Min Act: -0.0000

Data Index: 1179547 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.9667. Min Range: -0.9667

Max Act: 0.6608. Min Act: -0.0000

Data Index: 219668 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.9667. Min Range: -0.9667

Max Act: 0.7271. Min Act: -0.0000

Data Index: 429290 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.9667. Min Range: -0.9667

Max Act: 0.7218. Min Act: -0.0000

Data Index: 417070 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 0.9667. Min Range: -0.9667

Max Act: 0.7527. Min Act: -0.0000

Data Index: 97492 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.9667. Min Range: -0.9667

Max Act: 0.7231. Min Act: -0.0000

Data Index: 240124 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.9667. Min Range: -0.9667

Max Act: 0.7345. Min Act: -0.0000

Data Index: 892673 (C4 (Web Text))

Max Activating Token Index: 316