Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3044 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.4461. Min Act: -0.0000

Data Index: 3686 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.4394. Min Act: -0.0000

Data Index: 991699 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.4352. Min Act: -0.0000

Data Index: 193937 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.4456. Min Act: -0.0000

Data Index: 524296 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.4424. Min Act: -0.0000

Data Index: 214626 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.4215. Min Act: -0.0000

Data Index: 302986 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1029017 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.3923. Min Act: -0.0000

Data Index: 926160 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.3916. Min Act: -0.0000

Data Index: 1093167 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.3906. Min Act: -0.0000

Data Index: 901795 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1353800 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1289196 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.3938. Min Act: -0.0000

Data Index: 1139927 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.3808. Min Act: -0.0000

Data Index: 714308 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.3774. Min Act: -0.0000

Data Index: 1146279 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.3638. Min Act: -0.0000

Data Index: 1109709 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.3861. Min Act: -0.0000

Data Index: 1207453 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1553888 (Python Code)

Max Activating Token Index: 128

Text #18

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.3454. Min Act: -0.0000

Data Index: 826323 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.4461. Min Range: -0.4461

Max Act: 0.3695. Min Act: -0.0000

Data Index: 923468 (C4 (Web Text))

Max Activating Token Index: 338