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

Dataset: The Pile

Neuron 3589 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.6597. Min Act: -0.0000

Data Index: 292109 (The Pile)

Max Activating Token Index: 295

Text #1

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5470. Min Act: -0.0000

Data Index: 1141200 (The Pile)

Max Activating Token Index: 990

Text #2

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5851. Min Act: -0.0000

Data Index: 5241 (The Pile)

Max Activating Token Index: 942

Text #3

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5673. Min Act: -0.0000

Data Index: 1673302 (The Pile)

Max Activating Token Index: 194

Text #4

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5196. Min Act: -0.0000

Data Index: 34201 (The Pile)

Max Activating Token Index: 561

Text #5

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5536. Min Act: -0.0000

Data Index: 1742605 (The Pile)

Max Activating Token Index: 759

Text #6

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1296111 (The Pile)

Max Activating Token Index: 316

Text #7

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1745242 (The Pile)

Max Activating Token Index: 681

Text #8

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1713233 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.4733. Min Act: -0.0000

Data Index: 864140 (The Pile)

Max Activating Token Index: 831

Text #10

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.4562. Min Act: -0.0000

Data Index: 120527 (The Pile)

Max Activating Token Index: 183

Text #11

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.5010. Min Act: -0.0000

Data Index: 852763 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.4364. Min Act: -0.0000

Data Index: 1961039 (The Pile)

Max Activating Token Index: 579

Text #13

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.4576. Min Act: -0.0000

Data Index: 973978 (The Pile)

Max Activating Token Index: 579

Text #14

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.4439. Min Act: -0.0000

Data Index: 925164 (The Pile)

Max Activating Token Index: 432

Text #15

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1555296 (The Pile)

Max Activating Token Index: 429

Text #16

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.4492. Min Act: -0.0000

Data Index: 626539 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.4421. Min Act: -0.0000

Data Index: 839356 (The Pile)

Max Activating Token Index: 187

Text #18

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.4514. Min Act: -0.0000

Data Index: 127248 (The Pile)

Max Activating Token Index: 317

Text #19

Max Range: 0.6597. Min Range: -0.6597

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1370106 (The Pile)

Max Activating Token Index: 882