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

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

Neuron 1101 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: 2.5913. Min Range: -2.5913

Max Act: 2.5913. Min Act: -0.0000

Data Index: 564642 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.3702. Min Act: -0.0000

Data Index: 692298 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.3499. Min Act: -0.0000

Data Index: 1318667 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.4752. Min Act: -0.0000

Data Index: 238576 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.2559. Min Act: -0.0000

Data Index: 1028234 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.2503. Min Act: -0.0000

Data Index: 846228 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.1951. Min Act: -0.0000

Data Index: 532022 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.1745. Min Act: -0.0000

Data Index: 936611 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.0626. Min Act: -0.0000

Data Index: 1274836 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.1818. Min Act: -0.0000

Data Index: 956830 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.1673. Min Act: -0.0000

Data Index: 417070 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.1241. Min Act: -0.0000

Data Index: 484023 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.0463. Min Act: -0.0000

Data Index: 1205457 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.0324. Min Act: -0.0000

Data Index: 785572 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 2.5913. Min Range: -2.5913

Max Act: 1.8013. Min Act: -0.0000

Data Index: 419347 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 2.5913. Min Range: -2.5913

Max Act: 1.9265. Min Act: -0.0000

Data Index: 1083412 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.0228. Min Act: -0.0000

Data Index: 205267 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 2.5913. Min Range: -2.5913

Max Act: 2.0041. Min Act: -0.0000

Data Index: 670641 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 2.5913. Min Range: -2.5913

Max Act: 1.9981. Min Act: -0.0000

Data Index: 1064870 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 2.5913. Min Range: -2.5913

Max Act: 1.9822. Min Act: -0.0000

Data Index: 1121587 (C4 (Web Text))

Max Activating Token Index: 824