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

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

Neuron 3650 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5867. Min Act: -0.0000

Data Index: 1186771 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5787. Min Act: -0.0000

Data Index: 342938 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1258057 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5563. Min Act: -0.0000

Data Index: 296640 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5395. Min Act: -0.0000

Data Index: 138153 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5742. Min Act: -0.0000

Data Index: 791692 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5541. Min Act: -0.0000

Data Index: 602212 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5079. Min Act: -0.0000

Data Index: 692814 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4823. Min Act: -0.0000

Data Index: 468996 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1278098 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4934. Min Act: -0.0000

Data Index: 52621 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4767. Min Act: -0.0000

Data Index: 67790 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4966. Min Act: -0.0000

Data Index: 844227 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4647. Min Act: -0.0000

Data Index: 381874 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1011250 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4338. Min Act: -0.0000

Data Index: 29686 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4469. Min Act: -0.0000

Data Index: 805094 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4594. Min Act: -0.0000

Data Index: 599755 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4426. Min Act: -0.0000

Data Index: 976320 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4391. Min Act: -0.0000

Data Index: 111659 (C4 (Web Text))

Max Activating Token Index: 446