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

Dataset: The Pile

Neuron 3358 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.6652. Min Act: -0.0000

Data Index: 1749736 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.3561. Min Act: -0.0000

Data Index: 1726892 (The Pile)

Max Activating Token Index: 471

Text #2

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.2804. Min Act: -0.0000

Data Index: 57833 (The Pile)

Max Activating Token Index: 464

Text #3

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.2761. Min Act: -0.0000

Data Index: 1591909 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.1981. Min Act: -0.0000

Data Index: 709632 (The Pile)

Max Activating Token Index: 842

Text #5

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.1866. Min Act: -0.0000

Data Index: 862569 (The Pile)

Max Activating Token Index: 567

Text #6

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.1785. Min Act: -0.0000

Data Index: 214005 (The Pile)

Max Activating Token Index: 458

Text #7

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.2540. Min Act: -0.0000

Data Index: 1128554 (The Pile)

Max Activating Token Index: 914

Text #8

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.1077. Min Act: -0.0000

Data Index: 998693 (The Pile)

Max Activating Token Index: 142

Text #9

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.0354. Min Act: -0.0000

Data Index: 1293224 (The Pile)

Max Activating Token Index: 420

Text #10

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1836783 (The Pile)

Max Activating Token Index: 175

Text #11

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.0435. Min Act: -0.0000

Data Index: 718902 (The Pile)

Max Activating Token Index: 777

Text #12

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.0033. Min Act: -0.0000

Data Index: 1925475 (The Pile)

Max Activating Token Index: 712

Text #13

Max Range: 1.6652. Min Range: -1.6652

Max Act: 0.9288. Min Act: -0.0000

Data Index: 466507 (The Pile)

Max Activating Token Index: 514

Text #14

Max Range: 1.6652. Min Range: -1.6652

Max Act: 1.0558. Min Act: -0.0000

Data Index: 428208 (The Pile)

Max Activating Token Index: 814

Text #15

Max Range: 1.6652. Min Range: -1.6652

Max Act: 0.9915. Min Act: -0.0000

Data Index: 1088227 (The Pile)

Max Activating Token Index: 330

Text #16

Max Range: 1.6652. Min Range: -1.6652

Max Act: 0.9271. Min Act: -0.0000

Data Index: 632335 (The Pile)

Max Activating Token Index: 231

Text #17

Max Range: 1.6652. Min Range: -1.6652

Max Act: 0.9823. Min Act: -0.0000

Data Index: 623250 (The Pile)

Max Activating Token Index: 548

Text #18

Max Range: 1.6652. Min Range: -1.6652

Max Act: 0.9591. Min Act: -0.0000

Data Index: 460384 (The Pile)

Max Activating Token Index: 746

Text #19

Max Range: 1.6652. Min Range: -1.6652

Max Act: 0.9636. Min Act: -0.0000

Data Index: 728731 (The Pile)

Max Activating Token Index: 710