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

Dataset: The Pile

Neuron 3033 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: 3.3234. Min Range: -3.3234

Max Act: 3.3234. Min Act: -0.0000

Data Index: 1912289 (The Pile)

Max Activating Token Index: 762

Text #1

Max Range: 3.3234. Min Range: -3.3234

Max Act: 3.2035. Min Act: -0.0000

Data Index: 949276 (The Pile)

Max Activating Token Index: 68

Text #2

Max Range: 3.3234. Min Range: -3.3234

Max Act: 3.0183. Min Act: -0.0000

Data Index: 1244298 (The Pile)

Max Activating Token Index: 817

Text #3

Max Range: 3.3234. Min Range: -3.3234

Max Act: 3.1662. Min Act: -0.0000

Data Index: 1840722 (The Pile)

Max Activating Token Index: 773

Text #4

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.8904. Min Act: -0.0000

Data Index: 1899560 (The Pile)

Max Activating Token Index: 632

Text #5

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.5407. Min Act: -0.0000

Data Index: 1041783 (The Pile)

Max Activating Token Index: 469

Text #6

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.6407. Min Act: -0.0000

Data Index: 1292798 (The Pile)

Max Activating Token Index: 812

Text #7

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.3938. Min Act: -0.0000

Data Index: 288635 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.6486. Min Act: -0.0000

Data Index: 1578106 (The Pile)

Max Activating Token Index: 166

Text #9

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.5955. Min Act: -0.0000

Data Index: 581437 (The Pile)

Max Activating Token Index: 147

Text #10

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.6951. Min Act: -0.0000

Data Index: 824493 (The Pile)

Max Activating Token Index: 611

Text #11

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.3249. Min Act: -0.0000

Data Index: 1995359 (The Pile)

Max Activating Token Index: 116

Text #12

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.5685. Min Act: -0.0000

Data Index: 1897677 (The Pile)

Max Activating Token Index: 38

Text #13

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.5476. Min Act: -0.0000

Data Index: 1711927 (The Pile)

Max Activating Token Index: 271

Text #14

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.5599. Min Act: -0.0000

Data Index: 1097750 (The Pile)

Max Activating Token Index: 43

Text #15

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.6485. Min Act: -0.0000

Data Index: 98451 (The Pile)

Max Activating Token Index: 300

Text #16

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.3677. Min Act: -0.0000

Data Index: 621582 (The Pile)

Max Activating Token Index: 289

Text #17

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.4803. Min Act: -0.0000

Data Index: 587548 (The Pile)

Max Activating Token Index: 437

Text #18

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.4890. Min Act: -0.0000

Data Index: 1457479 (The Pile)

Max Activating Token Index: 740

Text #19

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.3298. Min Act: -0.0000

Data Index: 1861538 (The Pile)

Max Activating Token Index: 60