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

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

Neuron 3073 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9030. Min Range: -2.9030

Max Act: 2.9030. Min Act: 0.0000

Data Index: 820554 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 2.9030. Min Range: -2.9030

Max Act: 2.8172. Min Act: -0.0000

Data Index: 184942 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 2.9030. Min Range: -2.9030

Max Act: 2.7598. Min Act: -0.0000

Data Index: 1090655 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 2.9030. Min Range: -2.9030

Max Act: 2.6503. Min Act: -0.0000

Data Index: 725045 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 2.9030. Min Range: -2.9030

Max Act: 2.6529. Min Act: -0.0000

Data Index: 1306723 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 2.9030. Min Range: -2.9030

Max Act: 2.8893. Min Act: -0.0000

Data Index: 1216506 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 2.9030. Min Range: -2.9030

Max Act: 2.4758. Min Act: -0.0000

Data Index: 481880 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 2.9030. Min Range: -2.9030

Max Act: 2.4616. Min Act: -0.0000

Data Index: 828077 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 2.9030. Min Range: -2.9030

Max Act: 2.5276. Min Act: -0.0000

Data Index: 515513 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 2.9030. Min Range: -2.9030

Max Act: 2.3507. Min Act: -0.0000

Data Index: 964447 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 2.9030. Min Range: -2.9030

Max Act: 2.4800. Min Act: -0.0000

Data Index: 444947 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 2.9030. Min Range: -2.9030

Max Act: 2.3384. Min Act: -0.0000

Data Index: 1136138 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 2.9030. Min Range: -2.9030

Max Act: 2.2262. Min Act: -0.0000

Data Index: 139339 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 2.9030. Min Range: -2.9030

Max Act: 2.5815. Min Act: -0.0000

Data Index: 533656 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 2.9030. Min Range: -2.9030

Max Act: 2.3413. Min Act: -0.0000

Data Index: 35281 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 2.9030. Min Range: -2.9030

Max Act: 2.2866. Min Act: -0.0000

Data Index: 876528 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 2.9030. Min Range: -2.9030

Max Act: 2.3652. Min Act: -0.0000

Data Index: 243957 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 2.9030. Min Range: -2.9030

Max Act: 2.1403. Min Act: -0.0000

Data Index: 1194889 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 2.9030. Min Range: -2.9030

Max Act: 1.9749. Min Act: -0.0000

Data Index: 119164 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 2.9030. Min Range: -2.9030

Max Act: 2.1714. Min Act: -0.0000

Data Index: 1114533 (C4 (Web Text))

Max Activating Token Index: 491