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

Dataset: The Pile

Neuron 3993 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: 0.7271. Min Range: -0.7271

Max Act: 0.7271. Min Act: -0.0000

Data Index: 482717 (The Pile)

Max Activating Token Index: 973

Text #1

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1306370 (The Pile)

Max Activating Token Index: 683

Text #2

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.6824. Min Act: -0.0000

Data Index: 887346 (The Pile)

Max Activating Token Index: 710

Text #3

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.6210. Min Act: -0.0000

Data Index: 20618 (The Pile)

Max Activating Token Index: 939

Text #4

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.6226. Min Act: -0.0000

Data Index: 336797 (The Pile)

Max Activating Token Index: 911

Text #5

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1450042 (The Pile)

Max Activating Token Index: 328

Text #6

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1404118 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5451. Min Act: -0.0000

Data Index: 84014 (The Pile)

Max Activating Token Index: 918

Text #8

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5412. Min Act: -0.0000

Data Index: 1809537 (The Pile)

Max Activating Token Index: 975

Text #9

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1288648 (The Pile)

Max Activating Token Index: 1001

Text #10

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1531362 (The Pile)

Max Activating Token Index: 738

Text #11

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5825. Min Act: -0.0000

Data Index: 21327 (The Pile)

Max Activating Token Index: 978

Text #12

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.4780. Min Act: -0.0000

Data Index: 1591426 (The Pile)

Max Activating Token Index: 895

Text #13

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5428. Min Act: -0.0000

Data Index: 856916 (The Pile)

Max Activating Token Index: 852

Text #14

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5196. Min Act: -0.0000

Data Index: 1857843 (The Pile)

Max Activating Token Index: 510

Text #15

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5379. Min Act: -0.0000

Data Index: 597843 (The Pile)

Max Activating Token Index: 340

Text #16

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5362. Min Act: -0.0000

Data Index: 560368 (The Pile)

Max Activating Token Index: 855

Text #17

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.4807. Min Act: -0.0000

Data Index: 1682248 (The Pile)

Max Activating Token Index: 372

Text #18

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.6232. Min Act: -0.0000

Data Index: 1465544 (The Pile)

Max Activating Token Index: 838

Text #19

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.4807. Min Act: -0.0000

Data Index: 544939 (The Pile)

Max Activating Token Index: 662