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

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

Neuron 3772 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1888. Min Range: -2.1888

Max Act: 2.1888. Min Act: -0.0000

Data Index: 299448 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 2.1888. Min Range: -2.1888

Max Act: 2.0234. Min Act: -0.0000

Data Index: 236165 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 2.1888. Min Range: -2.1888

Max Act: 1.8445. Min Act: -0.0000

Data Index: 1075200 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 2.1888. Min Range: -2.1888

Max Act: 1.9903. Min Act: -0.0000

Data Index: 1284492 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 2.1888. Min Range: -2.1888

Max Act: 1.8442. Min Act: -0.0000

Data Index: 63452 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 2.1888. Min Range: -2.1888

Max Act: 1.8393. Min Act: -0.0000

Data Index: 968333 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 2.1888. Min Range: -2.1888

Max Act: 1.8082. Min Act: -0.0000

Data Index: 1177965 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 2.1888. Min Range: -2.1888

Max Act: 1.7540. Min Act: -0.0000

Data Index: 48894 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 2.1888. Min Range: -2.1888

Max Act: 1.6978. Min Act: -0.0000

Data Index: 349161 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 2.1888. Min Range: -2.1888

Max Act: 1.7109. Min Act: -0.0000

Data Index: 1277909 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 2.1888. Min Range: -2.1888

Max Act: 1.5802. Min Act: -0.0000

Data Index: 357929 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 2.1888. Min Range: -2.1888

Max Act: 1.6898. Min Act: -0.0000

Data Index: 446569 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 2.1888. Min Range: -2.1888

Max Act: 1.7627. Min Act: -0.0000

Data Index: 207022 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 2.1888. Min Range: -2.1888

Max Act: 1.6403. Min Act: -0.0000

Data Index: 818941 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 2.1888. Min Range: -2.1888

Max Act: 1.6440. Min Act: -0.0000

Data Index: 585642 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 2.1888. Min Range: -2.1888

Max Act: 1.6224. Min Act: -0.0000

Data Index: 383964 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 2.1888. Min Range: -2.1888

Max Act: 1.5460. Min Act: -0.0000

Data Index: 871533 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 2.1888. Min Range: -2.1888

Max Act: 1.6318. Min Act: -0.0000

Data Index: 1308192 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 2.1888. Min Range: -2.1888

Max Act: 1.4967. Min Act: -0.0000

Data Index: 518061 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 2.1888. Min Range: -2.1888

Max Act: 1.6720. Min Act: -0.0000

Data Index: 898985 (C4 (Web Text))

Max Activating Token Index: 635