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

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

Neuron 4438 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0850. Min Range: -3.0850

Max Act: 3.0850. Min Act: -0.0001

Data Index: 345358 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 3.0850. Min Range: -3.0850

Max Act: 2.9382. Min Act: -0.0000

Data Index: 677771 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 3.0850. Min Range: -3.0850

Max Act: 2.8162. Min Act: -0.0000

Data Index: 718136 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 3.0850. Min Range: -3.0850

Max Act: 2.6367. Min Act: -0.0000

Data Index: 239959 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 3.0850. Min Range: -3.0850

Max Act: 2.4695. Min Act: -0.0000

Data Index: 1003116 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 3.0850. Min Range: -3.0850

Max Act: 2.3895. Min Act: -0.0000

Data Index: 401828 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 3.0850. Min Range: -3.0850

Max Act: 2.4282. Min Act: -0.0000

Data Index: 1272654 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 3.0850. Min Range: -3.0850

Max Act: 2.2828. Min Act: -0.0000

Data Index: 967462 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 3.0850. Min Range: -3.0850

Max Act: 2.3849. Min Act: -0.0000

Data Index: 1179936 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 3.0850. Min Range: -3.0850

Max Act: 2.3887. Min Act: -0.0000

Data Index: 498634 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 3.0850. Min Range: -3.0850

Max Act: 2.0247. Min Act: -0.0000

Data Index: 547447 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 3.0850. Min Range: -3.0850

Max Act: 2.2978. Min Act: -0.0000

Data Index: 291530 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 3.0850. Min Range: -3.0850

Max Act: 2.2844. Min Act: -0.0000

Data Index: 1356142 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 3.0850. Min Range: -3.0850

Max Act: 1.9851. Min Act: -0.0000

Data Index: 495490 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 3.0850. Min Range: -3.0850

Max Act: 1.9582. Min Act: -0.0000

Data Index: 43784 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 3.0850. Min Range: -3.0850

Max Act: 1.7089. Min Act: -0.0000

Data Index: 1232452 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 3.0850. Min Range: -3.0850

Max Act: 1.8859. Min Act: -0.0000

Data Index: 1306021 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 3.0850. Min Range: -3.0850

Max Act: 1.7848. Min Act: -0.0000

Data Index: 62188 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 3.0850. Min Range: -3.0850

Max Act: 1.8836. Min Act: -0.0000

Data Index: 202257 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 3.0850. Min Range: -3.0850

Max Act: 1.8400. Min Act: -0.0000

Data Index: 1030927 (C4 (Web Text))

Max Activating Token Index: 526