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

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

Neuron 3504 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: 0.0923. Min Range: -0.0923

Max Act: 0.0916. Min Act: -0.0001

Data Index: 526377 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0907. Min Act: -0.0001

Data Index: 809195 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0883. Min Act: -0.0001

Data Index: 1149914 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0923. Min Act: -0.0001

Data Index: 223628 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0864. Min Act: -0.0001

Data Index: 86257 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0903. Min Act: -0.0001

Data Index: 908160 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0779. Min Act: -0.0001

Data Index: 757379 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0874. Min Act: -0.0001

Data Index: 545765 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1065091 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0834. Min Act: -0.0001

Data Index: 103554 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0858. Min Act: -0.0001

Data Index: 326059 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0854. Min Act: -0.0001

Data Index: 408521 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0816. Min Act: -0.0001

Data Index: 561372 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0813. Min Act: -0.0001

Data Index: 400133 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0765. Min Act: -0.0001

Data Index: 27435 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0741. Min Act: -0.0001

Data Index: 435605 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0768. Min Act: -0.0001

Data Index: 1268202 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0770. Min Act: -0.0001

Data Index: 82313 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0738. Min Act: -0.0001

Data Index: 431870 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0726. Min Act: -0.0001

Data Index: 45875 (C4 (Web Text))

Max Activating Token Index: 80