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

Dataset: The Pile

Neuron 3466 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3396. Min Range: -1.3396

Max Act: 1.3396. Min Act: -0.0000

Data Index: 1855615 (The Pile)

Max Activating Token Index: 931

Text #1

Max Range: 1.3396. Min Range: -1.3396

Max Act: 1.2742. Min Act: -0.0000

Data Index: 614950 (The Pile)

Max Activating Token Index: 456

Text #2

Max Range: 1.3396. Min Range: -1.3396

Max Act: 1.0483. Min Act: -0.0000

Data Index: 1315640 (The Pile)

Max Activating Token Index: 154

Text #3

Max Range: 1.3396. Min Range: -1.3396

Max Act: 0.9870. Min Act: -0.0000

Data Index: 1966566 (The Pile)

Max Activating Token Index: 573

Text #4

Max Range: 1.3396. Min Range: -1.3396

Max Act: 0.9797. Min Act: -0.0000

Data Index: 1009871 (The Pile)

Max Activating Token Index: 567

Text #5

Max Range: 1.3396. Min Range: -1.3396

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1596603 (The Pile)

Max Activating Token Index: 576

Text #6

Max Range: 1.3396. Min Range: -1.3396

Max Act: 1.0896. Min Act: -0.0000

Data Index: 1842914 (The Pile)

Max Activating Token Index: 867

Text #7

Max Range: 1.3396. Min Range: -1.3396

Max Act: 0.9706. Min Act: -0.0000

Data Index: 1655191 (The Pile)

Max Activating Token Index: 693

Text #8

Max Range: 1.3396. Min Range: -1.3396

Max Act: 0.9900. Min Act: -0.0000

Data Index: 434635 (The Pile)

Max Activating Token Index: 472

Text #9

Max Range: 1.3396. Min Range: -1.3396

Max Act: 1.1366. Min Act: -0.0000

Data Index: 1339744 (The Pile)

Max Activating Token Index: 182

Text #10

Max Range: 1.3396. Min Range: -1.3396

Max Act: 0.9238. Min Act: -0.0000

Data Index: 918859 (The Pile)

Max Activating Token Index: 523

Text #11

Max Range: 1.3396. Min Range: -1.3396

Max Act: 1.0308. Min Act: -0.0000

Data Index: 1831096 (The Pile)

Max Activating Token Index: 896

Text #12

Max Range: 1.3396. Min Range: -1.3396

Max Act: 0.9827. Min Act: -0.0000

Data Index: 1204725 (The Pile)

Max Activating Token Index: 950

Text #13

Max Range: 1.3396. Min Range: -1.3396

Max Act: 0.9212. Min Act: -0.0000

Data Index: 1745043 (The Pile)

Max Activating Token Index: 546

Text #14

Max Range: 1.3396. Min Range: -1.3396

Max Act: 0.9815. Min Act: -0.0000

Data Index: 345071 (The Pile)

Max Activating Token Index: 118

Text #15

Max Range: 1.3396. Min Range: -1.3396

Max Act: 1.0049. Min Act: -0.0000

Data Index: 1397053 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 1.3396. Min Range: -1.3396

Max Act: 0.9180. Min Act: -0.0000

Data Index: 361151 (The Pile)

Max Activating Token Index: 841

Text #17

Max Range: 1.3396. Min Range: -1.3396

Max Act: 0.9732. Min Act: -0.0000

Data Index: 147375 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 1.3396. Min Range: -1.3396

Max Act: 0.9147. Min Act: -0.0000

Data Index: 536908 (The Pile)

Max Activating Token Index: 829

Text #19

Max Range: 1.3396. Min Range: -1.3396

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1185807 (The Pile)

Max Activating Token Index: 922