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

Dataset: The Pile

Neuron 4606 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1962. Min Range: -1.1962

Max Act: 1.1587. Min Act: -0.0000

Data Index: 1572251 (The Pile)

Max Activating Token Index: 670

Text #1

Max Range: 1.1962. Min Range: -1.1962

Max Act: 1.1962. Min Act: -0.0000

Data Index: 1418095 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 1.1962. Min Range: -1.1962

Max Act: 1.0236. Min Act: -0.0000

Data Index: 846713 (The Pile)

Max Activating Token Index: 602

Text #3

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.9210. Min Act: -0.0000

Data Index: 247613 (The Pile)

Max Activating Token Index: 933

Text #4

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.7912. Min Act: -0.0000

Data Index: 1925808 (The Pile)

Max Activating Token Index: 421

Text #5

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.8093. Min Act: -0.0000

Data Index: 1244667 (The Pile)

Max Activating Token Index: 627

Text #6

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.7749. Min Act: -0.0000

Data Index: 1422090 (The Pile)

Max Activating Token Index: 870

Text #7

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.7099. Min Act: -0.0000

Data Index: 772052 (The Pile)

Max Activating Token Index: 522

Text #8

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.6935. Min Act: -0.0000

Data Index: 249791 (The Pile)

Max Activating Token Index: 566

Text #9

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1430816 (The Pile)

Max Activating Token Index: 895

Text #10

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.7832. Min Act: -0.0000

Data Index: 46638 (The Pile)

Max Activating Token Index: 475

Text #11

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.7630. Min Act: -0.0000

Data Index: 195231 (The Pile)

Max Activating Token Index: 283

Text #12

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1369151 (The Pile)

Max Activating Token Index: 869

Text #13

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1647944 (The Pile)

Max Activating Token Index: 898

Text #14

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.6674. Min Act: -0.0000

Data Index: 463422 (The Pile)

Max Activating Token Index: 800

Text #15

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.5514. Min Act: -0.0000

Data Index: 539494 (The Pile)

Max Activating Token Index: 633

Text #16

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.6561. Min Act: -0.0000

Data Index: 1053295 (The Pile)

Max Activating Token Index: 177

Text #17

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.6162. Min Act: -0.0000

Data Index: 284069 (The Pile)

Max Activating Token Index: 684

Text #18

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.7069. Min Act: -0.0000

Data Index: 106689 (The Pile)

Max Activating Token Index: 833

Text #19

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.6002. Min Act: -0.0000

Data Index: 1409904 (The Pile)

Max Activating Token Index: 179