Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1898 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.4203. Min Act: -0.0000

Data Index: 1390439 (The Pile)

Max Activating Token Index: 781

Text #1

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.0745. Min Act: -0.0000

Data Index: 921184 (The Pile)

Max Activating Token Index: 453

Text #2

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.0576. Min Act: -0.0000

Data Index: 1658962 (The Pile)

Max Activating Token Index: 117

Text #3

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.0494. Min Act: -0.0000

Data Index: 531676 (The Pile)

Max Activating Token Index: 936

Text #4

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.9464. Min Act: -0.0000

Data Index: 1486197 (The Pile)

Max Activating Token Index: 784

Text #5

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.1002. Min Act: -0.0000

Data Index: 966485 (The Pile)

Max Activating Token Index: 987

Text #6

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.0811. Min Act: -0.0000

Data Index: 1203495 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.9915. Min Act: -0.0000

Data Index: 1376003 (The Pile)

Max Activating Token Index: 926

Text #8

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.9655. Min Act: -0.0000

Data Index: 708981 (The Pile)

Max Activating Token Index: 954

Text #9

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.0189. Min Act: -0.0000

Data Index: 1557942 (The Pile)

Max Activating Token Index: 460

Text #10

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.8798. Min Act: -0.0000

Data Index: 578672 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.9731. Min Act: -0.0000

Data Index: 1298038 (The Pile)

Max Activating Token Index: 849

Text #12

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.8800. Min Act: -0.0000

Data Index: 1780444 (The Pile)

Max Activating Token Index: 588

Text #13

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.9742. Min Act: -0.0000

Data Index: 1613116 (The Pile)

Max Activating Token Index: 1010

Text #14

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.9863. Min Act: -0.0000

Data Index: 1888176 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1590827 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.9060. Min Act: -0.0000

Data Index: 518661 (The Pile)

Max Activating Token Index: 70

Text #17

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.7908. Min Act: -0.0000

Data Index: 633984 (The Pile)

Max Activating Token Index: 894

Text #18

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.8947. Min Act: -0.0000

Data Index: 1351440 (The Pile)

Max Activating Token Index: 328

Text #19

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.8572. Min Act: -0.0000

Data Index: 954691 (The Pile)

Max Activating Token Index: 301