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

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

Neuron 2598 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5173. Min Act: -0.0000

Data Index: 1499385 (Python Code)

Max Activating Token Index: 149

Text #1

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5877. Min Act: -0.0000

Data Index: 588556 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5552. Min Act: -0.0000

Data Index: 1031393 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5423. Min Act: -0.0000

Data Index: 1558547 (Python Code)

Max Activating Token Index: 158

Text #4

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5284. Min Act: -0.0000

Data Index: 856932 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5274. Min Act: -0.0000

Data Index: 443775 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1518960 (Python Code)

Max Activating Token Index: 192

Text #7

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4772. Min Act: -0.0000

Data Index: 1625338 (Python Code)

Max Activating Token Index: 276

Text #8

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4791. Min Act: -0.0000

Data Index: 1175539 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4818. Min Act: -0.0000

Data Index: 416294 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5053. Min Act: -0.0000

Data Index: 143872 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4728. Min Act: -0.0000

Data Index: 939724 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4899. Min Act: -0.0000

Data Index: 245613 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1533381 (Python Code)

Max Activating Token Index: 110

Text #14

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4882. Min Act: -0.0000

Data Index: 95765 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4835. Min Act: -0.0000

Data Index: 1635256 (Python Code)

Max Activating Token Index: 116

Text #16

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.5247. Min Act: -0.0000

Data Index: 1441792 (Python Code)

Max Activating Token Index: 117

Text #17

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4775. Min Act: -0.0000

Data Index: 771462 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4584. Min Act: -0.0000

Data Index: 510329 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.5877. Min Range: -0.5877

Max Act: 0.4130. Min Act: -0.0000

Data Index: 1596868 (Python Code)

Max Activating Token Index: 495