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

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

Neuron 670 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: 1.1413. Min Range: -1.1413

Max Act: 1.0883. Min Act: -0.0001

Data Index: 1344539 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 1.1413. Min Range: -1.1413

Max Act: 1.1413. Min Act: -0.0001

Data Index: 1250387 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.9726. Min Act: -0.0001

Data Index: 373940 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.9724. Min Act: -0.0001

Data Index: 1077778 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.8471. Min Act: -0.0001

Data Index: 108627 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.8296. Min Act: -0.0001

Data Index: 201024 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.8839. Min Act: -0.0001

Data Index: 1030350 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.8717. Min Act: -0.0001

Data Index: 330062 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.7457. Min Act: -0.0001

Data Index: 967425 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.8103. Min Act: -0.0001

Data Index: 890783 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.7636. Min Act: -0.0001

Data Index: 956012 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.8110. Min Act: -0.0001

Data Index: 1159382 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.7668. Min Act: -0.0001

Data Index: 413758 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.7538. Min Act: -0.0001

Data Index: 1343981 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.7019. Min Act: -0.0001

Data Index: 309636 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.7271. Min Act: -0.0001

Data Index: 45251 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.7728. Min Act: -0.0001

Data Index: 110170 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.6750. Min Act: -0.0001

Data Index: 1077305 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.6953. Min Act: -0.0001

Data Index: 1201417 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.7187. Min Act: -0.0001

Data Index: 146132 (C4 (Web Text))

Max Activating Token Index: 247