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

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

Neuron 3993 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: 3.3851. Min Range: -3.3851

Max Act: 3.3851. Min Act: -0.0000

Data Index: 135867 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 3.3851. Min Range: -3.3851

Max Act: 3.0936. Min Act: -0.0000

Data Index: 1011121 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 3.3851. Min Range: -3.3851

Max Act: 3.0734. Min Act: -0.0000

Data Index: 1322974 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 3.3851. Min Range: -3.3851

Max Act: 2.8964. Min Act: -0.0000

Data Index: 652265 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 3.3851. Min Range: -3.3851

Max Act: 2.6908. Min Act: -0.0000

Data Index: 951586 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 3.3851. Min Range: -3.3851

Max Act: 2.6592. Min Act: -0.0000

Data Index: 755824 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 3.3851. Min Range: -3.3851

Max Act: 2.4592. Min Act: -0.0000

Data Index: 1107422 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 3.3851. Min Range: -3.3851

Max Act: 2.4666. Min Act: -0.0000

Data Index: 440229 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 3.3851. Min Range: -3.3851

Max Act: 2.4563. Min Act: -0.0000

Data Index: 122737 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 3.3851. Min Range: -3.3851

Max Act: 2.4396. Min Act: -0.0000

Data Index: 23084 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 3.3851. Min Range: -3.3851

Max Act: 2.3010. Min Act: -0.0000

Data Index: 135628 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 3.3851. Min Range: -3.3851

Max Act: 2.5421. Min Act: -0.0000

Data Index: 400428 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 3.3851. Min Range: -3.3851

Max Act: 2.3721. Min Act: -0.0000

Data Index: 363671 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 3.3851. Min Range: -3.3851

Max Act: 2.1356. Min Act: -0.0000

Data Index: 1146659 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 3.3851. Min Range: -3.3851

Max Act: 2.3575. Min Act: -0.0000

Data Index: 14984 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 3.3851. Min Range: -3.3851

Max Act: 2.1881. Min Act: -0.0000

Data Index: 632739 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 3.3851. Min Range: -3.3851

Max Act: 2.1668. Min Act: -0.0000

Data Index: 82895 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 3.3851. Min Range: -3.3851

Max Act: 2.0654. Min Act: -0.0000

Data Index: 386020 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 3.3851. Min Range: -3.3851

Max Act: 2.2765. Min Act: -0.0000

Data Index: 802322 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 3.3851. Min Range: -3.3851

Max Act: 2.1534. Min Act: -0.0000

Data Index: 1310947 (C4 (Web Text))

Max Activating Token Index: 797