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

Dataset: The Pile

Neuron 5039 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: 0.7426. Min Range: -0.7426

Max Act: 0.7426. Min Act: 0.0000

Data Index: 1416964 (The Pile)

Max Activating Token Index: 850

Text #1

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6957. Min Act: -0.0000

Data Index: 1505591 (The Pile)

Max Activating Token Index: 100

Text #2

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6082. Min Act: -0.0000

Data Index: 106275 (The Pile)

Max Activating Token Index: 795

Text #3

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1388034 (The Pile)

Max Activating Token Index: 469

Text #4

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4948. Min Act: 0.0000

Data Index: 295704 (The Pile)

Max Activating Token Index: 885

Text #5

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5843. Min Act: 0.0000

Data Index: 998671 (The Pile)

Max Activating Token Index: 224

Text #6

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5382. Min Act: -0.0000

Data Index: 1989014 (The Pile)

Max Activating Token Index: 266

Text #7

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5303. Min Act: -0.0000

Data Index: 72677 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5251. Min Act: -0.0000

Data Index: 131458 (The Pile)

Max Activating Token Index: 847

Text #9

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5223. Min Act: -0.0000

Data Index: 1955764 (The Pile)

Max Activating Token Index: 290

Text #10

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1939090 (The Pile)

Max Activating Token Index: 266

Text #11

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6198. Min Act: -0.0000

Data Index: 742180 (The Pile)

Max Activating Token Index: 533

Text #12

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5353. Min Act: -0.0000

Data Index: 374537 (The Pile)

Max Activating Token Index: 133

Text #13

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4405. Min Act: -0.0000

Data Index: 391083 (The Pile)

Max Activating Token Index: 158

Text #14

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5160. Min Act: -0.0000

Data Index: 639301 (The Pile)

Max Activating Token Index: 159

Text #15

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5032. Min Act: -0.0000

Data Index: 242206 (The Pile)

Max Activating Token Index: 238

Text #16

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4999. Min Act: -0.0000

Data Index: 803250 (The Pile)

Max Activating Token Index: 228

Text #17

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5104. Min Act: -0.0000

Data Index: 1545663 (The Pile)

Max Activating Token Index: 454

Text #18

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4612. Min Act: -0.0000

Data Index: 273860 (The Pile)

Max Activating Token Index: 725

Text #19

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.4797. Min Act: 0.0000

Data Index: 1349439 (The Pile)

Max Activating Token Index: 874