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

Dataset: The Pile

Neuron 1123 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: 0.8234. Min Range: -0.8234

Max Act: 0.8234. Min Act: -0.0000

Data Index: 1464301 (The Pile)

Max Activating Token Index: 69

Text #1

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6388. Min Act: -0.0000

Data Index: 102472 (The Pile)

Max Activating Token Index: 186

Text #2

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1989607 (The Pile)

Max Activating Token Index: 874

Text #3

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1645487 (The Pile)

Max Activating Token Index: 634

Text #4

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1695612 (The Pile)

Max Activating Token Index: 285

Text #5

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5025. Min Act: -0.0000

Data Index: 411441 (The Pile)

Max Activating Token Index: 990

Text #6

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.4723. Min Act: -0.0000

Data Index: 540362 (The Pile)

Max Activating Token Index: 74

Text #7

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1735511 (The Pile)

Max Activating Token Index: 783

Text #8

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.4512. Min Act: -0.0000

Data Index: 613565 (The Pile)

Max Activating Token Index: 120

Text #9

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.4693. Min Act: -0.0000

Data Index: 1250580 (The Pile)

Max Activating Token Index: 771

Text #10

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1371874 (The Pile)

Max Activating Token Index: 987

Text #11

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.4843. Min Act: -0.0000

Data Index: 964316 (The Pile)

Max Activating Token Index: 386

Text #12

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1437728 (The Pile)

Max Activating Token Index: 755

Text #13

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.4616. Min Act: -0.0000

Data Index: 65985 (The Pile)

Max Activating Token Index: 736

Text #14

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1412640 (The Pile)

Max Activating Token Index: 522

Text #15

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.4705. Min Act: -0.0000

Data Index: 138347 (The Pile)

Max Activating Token Index: 58

Text #16

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.4456. Min Act: -0.0000

Data Index: 752898 (The Pile)

Max Activating Token Index: 782

Text #17

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.4419. Min Act: -0.0000

Data Index: 753688 (The Pile)

Max Activating Token Index: 381

Text #18

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.4426. Min Act: -0.0000

Data Index: 1488362 (The Pile)

Max Activating Token Index: 468

Text #19

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.4192. Min Act: -0.0000

Data Index: 681731 (The Pile)

Max Activating Token Index: 147