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

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

Neuron 5556 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4901. Min Range: -3.4901

Max Act: 3.4901. Min Act: -0.0000

Data Index: 389794 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 3.4901. Min Range: -3.4901

Max Act: 3.1823. Min Act: -0.0000

Data Index: 906014 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 3.4901. Min Range: -3.4901

Max Act: 3.1073. Min Act: -0.0000

Data Index: 734669 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 3.4901. Min Range: -3.4901

Max Act: 3.0703. Min Act: -0.0000

Data Index: 23649 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 3.4901. Min Range: -3.4901

Max Act: 2.9382. Min Act: -0.0000

Data Index: 318811 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 3.4901. Min Range: -3.4901

Max Act: 2.7349. Min Act: -0.0000

Data Index: 286535 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 3.4901. Min Range: -3.4901

Max Act: 2.7050. Min Act: -0.0000

Data Index: 894830 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 3.4901. Min Range: -3.4901

Max Act: 2.5695. Min Act: -0.0000

Data Index: 297838 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 3.4901. Min Range: -3.4901

Max Act: 2.5480. Min Act: -0.0000

Data Index: 137413 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 3.4901. Min Range: -3.4901

Max Act: 2.4984. Min Act: -0.0000

Data Index: 744730 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 3.4901. Min Range: -3.4901

Max Act: 2.3443. Min Act: -0.0000

Data Index: 797146 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 3.4901. Min Range: -3.4901

Max Act: 2.2244. Min Act: -0.0000

Data Index: 870364 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 3.4901. Min Range: -3.4901

Max Act: 2.5381. Min Act: -0.0000

Data Index: 619433 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 3.4901. Min Range: -3.4901

Max Act: 2.4186. Min Act: -0.0000

Data Index: 1051743 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 3.4901. Min Range: -3.4901

Max Act: 2.4206. Min Act: 0.0001

Data Index: 295707 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 3.4901. Min Range: -3.4901

Max Act: 2.5361. Min Act: -0.0000

Data Index: 1258061 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 3.4901. Min Range: -3.4901

Max Act: 2.5405. Min Act: -0.0000

Data Index: 871365 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 3.4901. Min Range: -3.4901

Max Act: 2.2533. Min Act: -0.0000

Data Index: 508143 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 3.4901. Min Range: -3.4901

Max Act: 2.3229. Min Act: -0.0000

Data Index: 363284 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 3.4901. Min Range: -3.4901

Max Act: 2.4350. Min Act: -0.0000

Data Index: 11110 (C4 (Web Text))

Max Activating Token Index: 25