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

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

Neuron 3231 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4407. Min Range: -2.4407

Max Act: 2.4407. Min Act: -0.0001

Data Index: 524516 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 2.4407. Min Range: -2.4407

Max Act: 2.4407. Min Act: -0.0001

Data Index: 469111 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 2.4407. Min Range: -2.4407

Max Act: 2.3646. Min Act: -0.0000

Data Index: 434827 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 2.4407. Min Range: -2.4407

Max Act: 2.2940. Min Act: -0.0000

Data Index: 1229809 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 2.4407. Min Range: -2.4407

Max Act: 2.4148. Min Act: -0.0000

Data Index: 1174860 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 2.4407. Min Range: -2.4407

Max Act: 2.0800. Min Act: -0.0000

Data Index: 1181259 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 2.4407. Min Range: -2.4407

Max Act: 1.9728. Min Act: -0.0000

Data Index: 564782 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 2.4407. Min Range: -2.4407

Max Act: 2.0546. Min Act: -0.0001

Data Index: 741305 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 2.4407. Min Range: -2.4407

Max Act: 2.1757. Min Act: -0.0001

Data Index: 642614 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 2.4407. Min Range: -2.4407

Max Act: 2.2631. Min Act: -0.0000

Data Index: 70023 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 2.4407. Min Range: -2.4407

Max Act: 2.0443. Min Act: -0.0000

Data Index: 295188 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 2.4407. Min Range: -2.4407

Max Act: 2.1192. Min Act: -0.0000

Data Index: 1078467 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 2.4407. Min Range: -2.4407

Max Act: 2.0553. Min Act: -0.0001

Data Index: 784409 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 2.4407. Min Range: -2.4407

Max Act: 1.9628. Min Act: -0.0001

Data Index: 642658 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 2.4407. Min Range: -2.4407

Max Act: 2.0639. Min Act: -0.0000

Data Index: 751026 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 2.4407. Min Range: -2.4407

Max Act: 2.1499. Min Act: -0.0000

Data Index: 831585 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 2.4407. Min Range: -2.4407

Max Act: 1.7008. Min Act: -0.0001

Data Index: 858523 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 2.4407. Min Range: -2.4407

Max Act: 1.9843. Min Act: -0.0000

Data Index: 1326989 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 2.4407. Min Range: -2.4407

Max Act: 2.0660. Min Act: -0.0001

Data Index: 404884 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 2.4407. Min Range: -2.4407

Max Act: 1.9593. Min Act: -0.0000

Data Index: 453988 (C4 (Web Text))

Max Activating Token Index: 31