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

Dataset: The Pile

Neuron 1332 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: 0.8337. Min Range: -0.8337

Max Act: 0.8337. Min Act: -0.0000

Data Index: 1071578 (The Pile)

Max Activating Token Index: 432

Text #1

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.8147. Min Act: -0.0000

Data Index: 1406619 (The Pile)

Max Activating Token Index: 392

Text #2

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7657. Min Act: -0.0000

Data Index: 1479190 (The Pile)

Max Activating Token Index: 468

Text #3

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7185. Min Act: -0.0000

Data Index: 89677 (The Pile)

Max Activating Token Index: 828

Text #4

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.6415. Min Act: -0.0000

Data Index: 1622060 (The Pile)

Max Activating Token Index: 575

Text #5

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.6326. Min Act: -0.0000

Data Index: 523529 (The Pile)

Max Activating Token Index: 102

Text #6

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1405487 (The Pile)

Max Activating Token Index: 865

Text #7

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.6396. Min Act: -0.0000

Data Index: 915928 (The Pile)

Max Activating Token Index: 682

Text #8

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1260926 (The Pile)

Max Activating Token Index: 754

Text #9

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1625288 (The Pile)

Max Activating Token Index: 170

Text #10

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.6743. Min Act: -0.0000

Data Index: 1145043 (The Pile)

Max Activating Token Index: 480

Text #11

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.6761. Min Act: -0.0000

Data Index: 902188 (The Pile)

Max Activating Token Index: 296

Text #12

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.5783. Min Act: -0.0000

Data Index: 303686 (The Pile)

Max Activating Token Index: 68

Text #13

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.4888. Min Act: -0.0000

Data Index: 1975006 (The Pile)

Max Activating Token Index: 673

Text #14

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.5463. Min Act: -0.0000

Data Index: 1149133 (The Pile)

Max Activating Token Index: 537

Text #15

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1656338 (The Pile)

Max Activating Token Index: 686

Text #16

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.5947. Min Act: -0.0000

Data Index: 124472 (The Pile)

Max Activating Token Index: 934

Text #17

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.5442. Min Act: -0.0000

Data Index: 618813 (The Pile)

Max Activating Token Index: 951

Text #18

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1777772 (The Pile)

Max Activating Token Index: 192

Text #19

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.5694. Min Act: -0.0000

Data Index: 802543 (The Pile)

Max Activating Token Index: 773