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

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

Neuron 2490 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5684. Min Act: -0.0000

Data Index: 441104 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4132. Min Act: -0.0000

Data Index: 424647 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1086935 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3936. Min Act: -0.0000

Data Index: 1243923 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3568. Min Act: -0.0000

Data Index: 1101768 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3485. Min Act: -0.0000

Data Index: 480314 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3425. Min Act: -0.0000

Data Index: 9958 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3367. Min Act: -0.0000

Data Index: 412223 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3255. Min Act: -0.0000

Data Index: 742221 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3237. Min Act: -0.0000

Data Index: 408071 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3194. Min Act: -0.0000

Data Index: 508132 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3184. Min Act: -0.0000

Data Index: 1016573 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3137. Min Act: -0.0000

Data Index: 835545 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3247. Min Act: -0.0000

Data Index: 860916 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3255. Min Act: -0.0000

Data Index: 1022324 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.3044. Min Act: -0.0000

Data Index: 278752 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.2990. Min Act: 0.0000

Data Index: 11711 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.2817. Min Act: -0.0000

Data Index: 76692 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.2915. Min Act: -0.0000

Data Index: 113431 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.2700. Min Act: -0.0000

Data Index: 692236 (C4 (Web Text))

Max Activating Token Index: 147