Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2980 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.5303. Min Act: -0.0002

Data Index: 827683 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.4909. Min Act: -0.0002

Data Index: 902394 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.1664. Min Act: -0.0001

Data Index: 931977 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.4548. Min Act: -0.0001

Data Index: 1175923 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.2796. Min Act: -0.0001

Data Index: 94069 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.2683. Min Act: -0.0002

Data Index: 1151995 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.2562. Min Act: -0.0002

Data Index: 479392 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.3226. Min Act: -0.0002

Data Index: 318926 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.3545. Min Act: -0.0002

Data Index: 16107 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.2522. Min Act: -0.0001

Data Index: 1109611 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.3115. Min Act: -0.0002

Data Index: 962874 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.2906. Min Act: -0.0002

Data Index: 919111 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.2632. Min Act: -0.0002

Data Index: 332859 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.2625. Min Act: -0.0001

Data Index: 1108315 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.2189. Min Act: -0.0002

Data Index: 1216461 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.0300. Min Act: -0.0002

Data Index: 699334 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.1355. Min Act: -0.0001

Data Index: 720498 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.2377. Min Act: -0.0001

Data Index: 188913 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.2649. Min Act: -0.0002

Data Index: 578579 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.1947. Min Act: -0.0001

Data Index: 1245827 (C4 (Web Text))

Max Activating Token Index: 85