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

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

Neuron 1834 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.9120. Min Act: -0.0001

Data Index: 789694 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.8717. Min Act: -0.0001

Data Index: 1056355 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.8682. Min Act: -0.0001

Data Index: 1174393 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.8376. Min Act: -0.0001

Data Index: 66570 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.8866. Min Act: -0.0001

Data Index: 614056 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.8299. Min Act: -0.0001

Data Index: 8213 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.7974. Min Act: -0.0001

Data Index: 156373 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.7895. Min Act: -0.0001

Data Index: 955656 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.7783. Min Act: -0.0001

Data Index: 214140 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.7910. Min Act: -0.0001

Data Index: 896373 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.7861. Min Act: -0.0001

Data Index: 533744 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.8119. Min Act: -0.0001

Data Index: 435866 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.7616. Min Act: -0.0001

Data Index: 693023 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.7547. Min Act: -0.0001

Data Index: 612647 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.7819. Min Act: -0.0001

Data Index: 1298910 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.7270. Min Act: -0.0001

Data Index: 502529 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.7326. Min Act: -0.0001

Data Index: 927360 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.7487. Min Act: -0.0001

Data Index: 535955 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.7444. Min Act: -0.0001

Data Index: 81084 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.7175. Min Act: -0.0001

Data Index: 226463 (C4 (Web Text))

Max Activating Token Index: 107