Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3790 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1271941 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.5654. Min Act: -0.0000

Data Index: 303470 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.4513. Min Act: -0.0000

Data Index: 963697 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.4394. Min Act: -0.0000

Data Index: 650535 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.4384. Min Act: -0.0000

Data Index: 1146906 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3780. Min Act: -0.0000

Data Index: 266162 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.4082. Min Act: -0.0000

Data Index: 660794 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3865. Min Act: -0.0000

Data Index: 652087 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3977. Min Act: -0.0000

Data Index: 45738 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3975. Min Act: -0.0000

Data Index: 812999 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3955. Min Act: -0.0000

Data Index: 812591 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.4059. Min Act: -0.0000

Data Index: 116699 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3778. Min Act: -0.0000

Data Index: 975904 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3892. Min Act: -0.0000

Data Index: 1242350 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.4000. Min Act: -0.0000

Data Index: 745021 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1257239 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3762. Min Act: -0.0000

Data Index: 251648 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3628. Min Act: -0.0000

Data Index: 526037 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3599. Min Act: -0.0000

Data Index: 520462 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3710. Min Act: -0.0000

Data Index: 121521 (C4 (Web Text))

Max Activating Token Index: 651