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

Dataset: The Pile

Neuron 3439 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.5848. Min Act: -0.0000

Data Index: 209782 (The Pile)

Max Activating Token Index: 458

Text #1

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.4121. Min Act: -0.0000

Data Index: 1561046 (The Pile)

Max Activating Token Index: 505

Text #2

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.3105. Min Act: -0.0000

Data Index: 1538953 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.3168. Min Act: -0.0000

Data Index: 1745435 (The Pile)

Max Activating Token Index: 552

Text #4

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.4722. Min Act: -0.0000

Data Index: 142404 (The Pile)

Max Activating Token Index: 483

Text #5

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.4637. Min Act: -0.0000

Data Index: 1841159 (The Pile)

Max Activating Token Index: 445

Text #6

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.4172. Min Act: -0.0000

Data Index: 1543683 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.1810. Min Act: -0.0000

Data Index: 1186259 (The Pile)

Max Activating Token Index: 761

Text #8

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.3210. Min Act: -0.0000

Data Index: 262155 (The Pile)

Max Activating Token Index: 166

Text #9

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.2459. Min Act: -0.0000

Data Index: 1649015 (The Pile)

Max Activating Token Index: 835

Text #10

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.3589. Min Act: -0.0000

Data Index: 173533 (The Pile)

Max Activating Token Index: 205

Text #11

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.3135. Min Act: -0.0000

Data Index: 1953283 (The Pile)

Max Activating Token Index: 383

Text #12

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.2856. Min Act: -0.0000

Data Index: 1421373 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.4307. Min Act: -0.0000

Data Index: 437068 (The Pile)

Max Activating Token Index: 673

Text #14

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.3519. Min Act: -0.0000

Data Index: 1379007 (The Pile)

Max Activating Token Index: 871

Text #15

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.3084. Min Act: -0.0000

Data Index: 1826868 (The Pile)

Max Activating Token Index: 388

Text #16

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.2665. Min Act: -0.0000

Data Index: 630023 (The Pile)

Max Activating Token Index: 863

Text #17

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.3414. Min Act: -0.0000

Data Index: 155471 (The Pile)

Max Activating Token Index: 615

Text #18

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1117129 (The Pile)

Max Activating Token Index: 238

Text #19

Max Range: 1.5848. Min Range: -1.5848

Max Act: 1.2939. Min Act: -0.0000

Data Index: 1661542 (The Pile)

Max Activating Token Index: 148