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

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

Neuron 2507 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.1452. Min Act: -0.0000

Data Index: 831098 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 3.1452. Min Range: -3.1452

Max Act: 2.6292. Min Act: -0.0000

Data Index: 783221 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 3.1452. Min Range: -3.1452

Max Act: 1.9670. Min Act: -0.0000

Data Index: 517456 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 3.1452. Min Range: -3.1452

Max Act: 2.5352. Min Act: -0.0000

Data Index: 852056 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 3.1452. Min Range: -3.1452

Max Act: 2.8369. Min Act: -0.0000

Data Index: 191741 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 3.1452. Min Range: -3.1452

Max Act: 2.4222. Min Act: -0.0000

Data Index: 658316 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 3.1452. Min Range: -3.1452

Max Act: 1.9212. Min Act: -0.0000

Data Index: 1262639 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 3.1452. Min Range: -3.1452

Max Act: 2.2792. Min Act: -0.0000

Data Index: 313781 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 3.1452. Min Range: -3.1452

Max Act: 2.8758. Min Act: -0.0000

Data Index: 373296 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 3.1452. Min Range: -3.1452

Max Act: 1.9473. Min Act: -0.0000

Data Index: 709886 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 3.1452. Min Range: -3.1452

Max Act: 2.4046. Min Act: -0.0000

Data Index: 152083 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 3.1452. Min Range: -3.1452

Max Act: 1.8067. Min Act: -0.0000

Data Index: 995003 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 3.1452. Min Range: -3.1452

Max Act: 2.2247. Min Act: -0.0000

Data Index: 1170017 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 3.1452. Min Range: -3.1452

Max Act: 1.9678. Min Act: -0.0000

Data Index: 80450 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 3.1452. Min Range: -3.1452

Max Act: 2.8677. Min Act: -0.0000

Data Index: 331674 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 3.1452. Min Range: -3.1452

Max Act: 2.1984. Min Act: -0.0000

Data Index: 122868 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 3.1452. Min Range: -3.1452

Max Act: 1.9645. Min Act: -0.0000

Data Index: 80033 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 3.1452. Min Range: -3.1452

Max Act: 1.8454. Min Act: -0.0000

Data Index: 22748 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 3.1452. Min Range: -3.1452

Max Act: 2.3554. Min Act: -0.0000

Data Index: 274814 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 3.1452. Min Range: -3.1452

Max Act: 1.9890. Min Act: -0.0000

Data Index: 665037 (C4 (Web Text))

Max Activating Token Index: 29