Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1412 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4376. Min Act: -0.0004

Data Index: 10218 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4592. Min Act: -0.0004

Data Index: 428317 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3423. Min Act: -0.0004

Data Index: 535737 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3284. Min Act: -0.0004

Data Index: 396410 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4333. Min Act: -0.0004

Data Index: 52545 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4396. Min Act: -0.0004

Data Index: 810052 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4126. Min Act: -0.0004

Data Index: 493089 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3488. Min Act: -0.0004

Data Index: 808828 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4474. Min Act: -0.0004

Data Index: 1299514 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3998. Min Act: -0.0004

Data Index: 707737 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4111. Min Act: -0.0004

Data Index: 1331235 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3820. Min Act: -0.0004

Data Index: 1015087 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3946. Min Act: -0.0004

Data Index: 1067453 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3926. Min Act: -0.0004

Data Index: 102404 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3650. Min Act: -0.0004

Data Index: 916475 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4196. Min Act: -0.0004

Data Index: 267093 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3929. Min Act: -0.0004

Data Index: 133692 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3844. Min Act: -0.0004

Data Index: 521236 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3962. Min Act: -0.0004

Data Index: 589461 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2998. Min Act: -0.0004

Data Index: 160423 (C4 (Web Text))

Max Activating Token Index: 826