Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2583 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3512. Min Range: -1.3512

Max Act: 1.3512. Min Act: -0.0001

Data Index: 160677 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 1.3512. Min Range: -1.3512

Max Act: 1.2028. Min Act: -0.0001

Data Index: 811428 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 1.3512. Min Range: -1.3512

Max Act: 1.1280. Min Act: -0.0001

Data Index: 425445 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 1.3512. Min Range: -1.3512

Max Act: 1.0637. Min Act: -0.0001

Data Index: 331733 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 1.3512. Min Range: -1.3512

Max Act: 1.0689. Min Act: -0.0001

Data Index: 95105 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 1.3512. Min Range: -1.3512

Max Act: 1.0588. Min Act: -0.0001

Data Index: 1116044 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 1.3512. Min Range: -1.3512

Max Act: 1.0413. Min Act: -0.0001

Data Index: 673817 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 1.3512. Min Range: -1.3512

Max Act: 0.9726. Min Act: -0.0001

Data Index: 617841 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 1.3512. Min Range: -1.3512

Max Act: 0.9778. Min Act: -0.0001

Data Index: 394321 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 1.3512. Min Range: -1.3512

Max Act: 0.9902. Min Act: -0.0001

Data Index: 241037 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 1.3512. Min Range: -1.3512

Max Act: 0.9261. Min Act: -0.0001

Data Index: 194205 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 1.3512. Min Range: -1.3512

Max Act: 1.0094. Min Act: -0.0001

Data Index: 63842 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 1.3512. Min Range: -1.3512

Max Act: 0.9735. Min Act: -0.0001

Data Index: 81887 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 1.3512. Min Range: -1.3512

Max Act: 0.9969. Min Act: -0.0001

Data Index: 977040 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 1.3512. Min Range: -1.3512

Max Act: 0.9202. Min Act: -0.0001

Data Index: 963637 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 1.3512. Min Range: -1.3512

Max Act: 0.9783. Min Act: -0.0001

Data Index: 845998 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 1.3512. Min Range: -1.3512

Max Act: 0.9393. Min Act: -0.0001

Data Index: 363684 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 1.3512. Min Range: -1.3512

Max Act: 0.9414. Min Act: -0.0001

Data Index: 965139 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 1.3512. Min Range: -1.3512

Max Act: 0.9305. Min Act: -0.0001

Data Index: 713446 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 1.3512. Min Range: -1.3512

Max Act: 0.9577. Min Act: -0.0001

Data Index: 1110915 (C4 (Web Text))

Max Activating Token Index: 569