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

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

Neuron 2994 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: 2.3710. Min Range: -2.3710

Max Act: 2.3550. Min Act: -0.0000

Data Index: 1112142 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 2.3710. Min Range: -2.3710

Max Act: 2.3710. Min Act: -0.0000

Data Index: 384521 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 2.3710. Min Range: -2.3710

Max Act: 2.2475. Min Act: -0.0000

Data Index: 133781 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 2.3710. Min Range: -2.3710

Max Act: 1.9320. Min Act: -0.0000

Data Index: 1264805 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 2.3710. Min Range: -2.3710

Max Act: 1.9272. Min Act: -0.0000

Data Index: 445239 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 2.3710. Min Range: -2.3710

Max Act: 1.8576. Min Act: -0.0000

Data Index: 165842 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 2.3710. Min Range: -2.3710

Max Act: 2.0007. Min Act: -0.0000

Data Index: 718664 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 2.3710. Min Range: -2.3710

Max Act: 1.6916. Min Act: -0.0000

Data Index: 1336075 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 2.3710. Min Range: -2.3710

Max Act: 1.9225. Min Act: -0.0000

Data Index: 443165 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 2.3710. Min Range: -2.3710

Max Act: 1.6860. Min Act: -0.0000

Data Index: 923609 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 2.3710. Min Range: -2.3710

Max Act: 1.7163. Min Act: -0.0000

Data Index: 665554 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 2.3710. Min Range: -2.3710

Max Act: 1.9128. Min Act: -0.0000

Data Index: 419924 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 2.3710. Min Range: -2.3710

Max Act: 1.8920. Min Act: -0.0000

Data Index: 1114498 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 2.3710. Min Range: -2.3710

Max Act: 1.7154. Min Act: -0.0000

Data Index: 181390 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 2.3710. Min Range: -2.3710

Max Act: 1.7338. Min Act: -0.0000

Data Index: 1054067 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 2.3710. Min Range: -2.3710

Max Act: 1.8551. Min Act: -0.0000

Data Index: 224310 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 2.3710. Min Range: -2.3710

Max Act: 1.6427. Min Act: -0.0000

Data Index: 54814 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 2.3710. Min Range: -2.3710

Max Act: 1.6957. Min Act: -0.0000

Data Index: 968997 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 2.3710. Min Range: -2.3710

Max Act: 1.8411. Min Act: -0.0000

Data Index: 348283 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 2.3710. Min Range: -2.3710

Max Act: 1.7785. Min Act: -0.0000

Data Index: 1320020 (C4 (Web Text))

Max Activating Token Index: 638