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

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

Neuron 302 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9871. Min Range: -3.9871

Max Act: 3.9481. Min Act: -0.0000

Data Index: 591939 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 3.9871. Min Range: -3.9871

Max Act: 3.9765. Min Act: -0.0000

Data Index: 1272790 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 3.9871. Min Range: -3.9871

Max Act: 3.6369. Min Act: -0.0000

Data Index: 880692 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 3.9871. Min Range: -3.9871

Max Act: 3.9871. Min Act: -0.0000

Data Index: 1281521 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 3.9871. Min Range: -3.9871

Max Act: 3.6663. Min Act: -0.0000

Data Index: 584524 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 3.9871. Min Range: -3.9871

Max Act: 3.4869. Min Act: -0.0000

Data Index: 287922 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 3.9871. Min Range: -3.9871

Max Act: 3.6306. Min Act: -0.0000

Data Index: 933647 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 3.9871. Min Range: -3.9871

Max Act: 3.3529. Min Act: -0.0000

Data Index: 632780 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 3.9871. Min Range: -3.9871

Max Act: 3.3448. Min Act: -0.0000

Data Index: 1003366 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 3.9871. Min Range: -3.9871

Max Act: 3.4485. Min Act: -0.0000

Data Index: 32352 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 3.9871. Min Range: -3.9871

Max Act: 3.1855. Min Act: -0.0000

Data Index: 969089 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 3.9871. Min Range: -3.9871

Max Act: 3.3314. Min Act: -0.0000

Data Index: 269142 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 3.9871. Min Range: -3.9871

Max Act: 3.3076. Min Act: -0.0000

Data Index: 811255 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 3.9871. Min Range: -3.9871

Max Act: 3.1462. Min Act: -0.0000

Data Index: 51251 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 3.9871. Min Range: -3.9871

Max Act: 3.1620. Min Act: -0.0000

Data Index: 1222775 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 3.9871. Min Range: -3.9871

Max Act: 2.9835. Min Act: -0.0000

Data Index: 544276 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 3.9871. Min Range: -3.9871

Max Act: 3.1028. Min Act: -0.0000

Data Index: 561929 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 3.9871. Min Range: -3.9871

Max Act: 2.8851. Min Act: -0.0000

Data Index: 564388 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 3.9871. Min Range: -3.9871

Max Act: 2.8652. Min Act: -0.0000

Data Index: 324499 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 3.9871. Min Range: -3.9871

Max Act: 2.6794. Min Act: -0.0000

Data Index: 497810 (C4 (Web Text))

Max Activating Token Index: 923