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

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

Neuron 1608 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0667. Min Range: -1.0667

Max Act: 1.0667. Min Act: -0.0001

Data Index: 950520 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.9524. Min Act: -0.0001

Data Index: 1107671 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.9899. Min Act: -0.0001

Data Index: 469299 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.9760. Min Act: -0.0001

Data Index: 564290 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.9322. Min Act: -0.0001

Data Index: 659336 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8707. Min Act: -0.0001

Data Index: 1351203 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.9167. Min Act: -0.0001

Data Index: 767118 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8785. Min Act: -0.0001

Data Index: 1161173 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8683. Min Act: -0.0001

Data Index: 819067 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.9231. Min Act: -0.0001

Data Index: 1214710 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8481. Min Act: -0.0001

Data Index: 854534 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.9025. Min Act: -0.0001

Data Index: 1166266 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8650. Min Act: -0.0001

Data Index: 78534 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8562. Min Act: -0.0001

Data Index: 1049891 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8569. Min Act: -0.0001

Data Index: 1046681 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8823. Min Act: -0.0001

Data Index: 905578 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.9033. Min Act: -0.0001

Data Index: 725964 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.9209. Min Act: -0.0001

Data Index: 745378 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7842. Min Act: -0.0001

Data Index: 919842 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.9031. Min Act: -0.0001

Data Index: 1164532 (C4 (Web Text))

Max Activating Token Index: 749