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

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

Neuron 302 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: 3.2608. Min Range: -3.2608

Max Act: 2.8535. Min Act: -0.0000

Data Index: 1351612 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 3.2608. Min Range: -3.2608

Max Act: 3.2608. Min Act: -0.0000

Data Index: 66557 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 3.2608. Min Range: -3.2608

Max Act: 2.8433. Min Act: -0.0000

Data Index: 961150 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 3.2608. Min Range: -3.2608

Max Act: 2.6975. Min Act: -0.0000

Data Index: 621225 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 3.2608. Min Range: -3.2608

Max Act: 2.5956. Min Act: -0.0000

Data Index: 1280636 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 3.2608. Min Range: -3.2608

Max Act: 2.7477. Min Act: -0.0000

Data Index: 1263552 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 3.2608. Min Range: -3.2608

Max Act: 2.5990. Min Act: -0.0000

Data Index: 895874 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 3.2608. Min Range: -3.2608

Max Act: 2.5943. Min Act: -0.0000

Data Index: 1257973 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 3.2608. Min Range: -3.2608

Max Act: 2.6861. Min Act: -0.0000

Data Index: 244668 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 3.2608. Min Range: -3.2608

Max Act: 2.6610. Min Act: -0.0000

Data Index: 338923 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 3.2608. Min Range: -3.2608

Max Act: 2.5197. Min Act: -0.0000

Data Index: 1134268 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 3.2608. Min Range: -3.2608

Max Act: 2.5109. Min Act: -0.0000

Data Index: 716389 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 3.2608. Min Range: -3.2608

Max Act: 2.6132. Min Act: -0.0000

Data Index: 1218822 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 3.2608. Min Range: -3.2608

Max Act: 2.5473. Min Act: -0.0000

Data Index: 67311 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 3.2608. Min Range: -3.2608

Max Act: 2.3915. Min Act: -0.0000

Data Index: 568365 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 3.2608. Min Range: -3.2608

Max Act: 2.6480. Min Act: -0.0000

Data Index: 445681 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 3.2608. Min Range: -3.2608

Max Act: 2.3406. Min Act: -0.0000

Data Index: 1061051 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 3.2608. Min Range: -3.2608

Max Act: 2.4480. Min Act: -0.0000

Data Index: 662419 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 3.2608. Min Range: -3.2608

Max Act: 2.1961. Min Act: -0.0000

Data Index: 211112 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 3.2608. Min Range: -3.2608

Max Act: 2.2645. Min Act: -0.0000

Data Index: 414670 (C4 (Web Text))

Max Activating Token Index: 112