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

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

Neuron 3655 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6677. Min Act: -0.0000

Data Index: 461660 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6632. Min Act: -0.0000

Data Index: 49791 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6526. Min Act: -0.0000

Data Index: 827022 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6750. Min Act: -0.0000

Data Index: 870394 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6336. Min Act: -0.0000

Data Index: 90640 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6278. Min Act: -0.0000

Data Index: 738120 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5924. Min Act: -0.0000

Data Index: 519464 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5867. Min Act: -0.0000

Data Index: 960236 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1030545 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5681. Min Act: -0.0000

Data Index: 433431 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5655. Min Act: -0.0000

Data Index: 616118 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5525. Min Act: -0.0000

Data Index: 1063053 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5465. Min Act: -0.0000

Data Index: 903714 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1205861 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5092. Min Act: -0.0000

Data Index: 693218 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5713. Min Act: -0.0000

Data Index: 21531 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5206. Min Act: -0.0000

Data Index: 999449 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5480. Min Act: -0.0000

Data Index: 341891 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5298. Min Act: -0.0000

Data Index: 615945 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5272. Min Act: -0.0000

Data Index: 716885 (C4 (Web Text))

Max Activating Token Index: 261