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

Dataset: The Pile

Neuron 2857 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.4495. Min Act: -0.0000

Data Index: 19760 (The Pile)

Max Activating Token Index: 144

Text #1

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.4139. Min Act: -0.0000

Data Index: 25654 (The Pile)

Max Activating Token Index: 282

Text #2

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.4099. Min Act: -0.0000

Data Index: 265793 (The Pile)

Max Activating Token Index: 68

Text #3

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1387234 (The Pile)

Max Activating Token Index: 185

Text #4

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.4086. Min Act: -0.0000

Data Index: 21926 (The Pile)

Max Activating Token Index: 779

Text #5

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3713. Min Act: -0.0000

Data Index: 519278 (The Pile)

Max Activating Token Index: 97

Text #6

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.4016. Min Act: -0.0000

Data Index: 332176 (The Pile)

Max Activating Token Index: 55

Text #7

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1407751 (The Pile)

Max Activating Token Index: 265

Text #8

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1838135 (The Pile)

Max Activating Token Index: 402

Text #9

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3545. Min Act: -0.0000

Data Index: 974729 (The Pile)

Max Activating Token Index: 246

Text #10

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3957. Min Act: -0.0000

Data Index: 1968423 (The Pile)

Max Activating Token Index: 677

Text #11

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3461. Min Act: -0.0000

Data Index: 814380 (The Pile)

Max Activating Token Index: 188

Text #12

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3387. Min Act: -0.0000

Data Index: 1485638 (The Pile)

Max Activating Token Index: 139

Text #13

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3413. Min Act: -0.0000

Data Index: 1049174 (The Pile)

Max Activating Token Index: 189

Text #14

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3496. Min Act: -0.0000

Data Index: 287696 (The Pile)

Max Activating Token Index: 38

Text #15

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3284. Min Act: -0.0000

Data Index: 1235572 (The Pile)

Max Activating Token Index: 340

Text #16

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3313. Min Act: -0.0000

Data Index: 538268 (The Pile)

Max Activating Token Index: 922

Text #17

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3676. Min Act: -0.0000

Data Index: 1364652 (The Pile)

Max Activating Token Index: 62

Text #18

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1055396 (The Pile)

Max Activating Token Index: 834

Text #19

Max Range: 0.4495. Min Range: -0.4495

Max Act: 0.2931. Min Act: -0.0000

Data Index: 204568 (The Pile)

Max Activating Token Index: 477