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

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

Neuron 3878 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.2345. Min Act: -0.0000

Data Index: 885215 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 1.3268. Min Range: -1.3268

Max Act: 1.3268. Min Act: -0.0000

Data Index: 1217888 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.9695. Min Act: -0.0000

Data Index: 356497 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1345035 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.9055. Min Act: -0.0000

Data Index: 97352 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.8625. Min Act: -0.0000

Data Index: 636315 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.8004. Min Act: -0.0000

Data Index: 542614 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1285501 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.8672. Min Act: -0.0000

Data Index: 974580 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.8407. Min Act: -0.0000

Data Index: 524665 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.8049. Min Act: -0.0000

Data Index: 668495 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.8532. Min Act: -0.0000

Data Index: 132195 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.7992. Min Act: -0.0000

Data Index: 855405 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.7637. Min Act: -0.0000

Data Index: 941848 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.6619. Min Act: -0.0000

Data Index: 775817 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.7633. Min Act: -0.0000

Data Index: 585327 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.8404. Min Act: -0.0000

Data Index: 852466 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.7821. Min Act: -0.0000

Data Index: 480388 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.7825. Min Act: -0.0000

Data Index: 651939 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 1.3268. Min Range: -1.3268

Max Act: 0.8193. Min Act: -0.0000

Data Index: 1026542 (C4 (Web Text))

Max Activating Token Index: 144