Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1931 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2661. Min Act: -0.0001

Data Index: 917029 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1916. Min Act: 0.0000

Data Index: 56339 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.2017. Min Act: -0.0000

Data Index: 930882 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1954. Min Act: -0.0001

Data Index: 1159905 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1879. Min Act: -0.0001

Data Index: 114397 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1966. Min Act: -0.0001

Data Index: 90069 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1795. Min Act: -0.0001

Data Index: 383371 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1808. Min Act: -0.0001

Data Index: 1231469 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1839. Min Act: -0.0001

Data Index: 536934 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1753. Min Act: -0.0001

Data Index: 25683 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1863. Min Act: -0.0001

Data Index: 663274 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1806. Min Act: -0.0001

Data Index: 903975 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1726. Min Act: -0.0001

Data Index: 1273963 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1792. Min Act: -0.0001

Data Index: 83762 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1771. Min Act: -0.0001

Data Index: 879605 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1747. Min Act: -0.0000

Data Index: 331781 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1801. Min Act: -0.0000

Data Index: 133603 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1709. Min Act: -0.0001

Data Index: 1183910 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1650. Min Act: -0.0001

Data Index: 177642 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 0.2661. Min Range: -0.2661

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1309437 (C4 (Web Text))

Max Activating Token Index: 812