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

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

Neuron 2978 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: 1.4443. Min Range: -1.4443

Max Act: 1.4072. Min Act: -0.0000

Data Index: 383200 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.4443. Min Act: -0.0000

Data Index: 1043989 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.1958. Min Act: -0.0000

Data Index: 1251624 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.1019. Min Act: -0.0000

Data Index: 104350 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.0963. Min Act: -0.0000

Data Index: 1020862 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.0826. Min Act: -0.0000

Data Index: 101005 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.0212. Min Act: -0.0000

Data Index: 1274580 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9633. Min Act: -0.0000

Data Index: 813454 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.0765. Min Act: -0.0000

Data Index: 997088 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.0030. Min Act: -0.0000

Data Index: 775886 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9287. Min Act: -0.0000

Data Index: 29126 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9863. Min Act: -0.0000

Data Index: 488484 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9779. Min Act: -0.0000

Data Index: 150536 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9622. Min Act: -0.0000

Data Index: 1153956 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9553. Min Act: -0.0000

Data Index: 593429 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1005376 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.8877. Min Act: -0.0000

Data Index: 156250 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9336. Min Act: -0.0000

Data Index: 1111282 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9214. Min Act: -0.0000

Data Index: 264454 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9219. Min Act: -0.0000

Data Index: 559539 (C4 (Web Text))

Max Activating Token Index: 925