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

Dataset: The Pile

Neuron 1962 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6435. Min Range: -5.6435

Max Act: 5.3773. Min Act: -0.0000

Data Index: 499996 (The Pile)

Max Activating Token Index: 849

Text #1

Max Range: 5.6435. Min Range: -5.6435

Max Act: 5.6435. Min Act: -0.0000

Data Index: 1504542 (The Pile)

Max Activating Token Index: 880

Text #2

Max Range: 5.6435. Min Range: -5.6435

Max Act: 5.1567. Min Act: -0.0000

Data Index: 1113701 (The Pile)

Max Activating Token Index: 365

Text #3

Max Range: 5.6435. Min Range: -5.6435

Max Act: 5.1337. Min Act: -0.0000

Data Index: 112063 (The Pile)

Max Activating Token Index: 327

Text #4

Max Range: 5.6435. Min Range: -5.6435

Max Act: 4.8934. Min Act: -0.0000

Data Index: 1425834 (The Pile)

Max Activating Token Index: 669

Text #5

Max Range: 5.6435. Min Range: -5.6435

Max Act: 4.7996. Min Act: -0.0000

Data Index: 1030423 (The Pile)

Max Activating Token Index: 926

Text #6

Max Range: 5.6435. Min Range: -5.6435

Max Act: 4.9922. Min Act: -0.0000

Data Index: 1679501 (The Pile)

Max Activating Token Index: 190

Text #7

Max Range: 5.6435. Min Range: -5.6435

Max Act: 4.7633. Min Act: -0.0000

Data Index: 740708 (The Pile)

Max Activating Token Index: 467

Text #8

Max Range: 5.6435. Min Range: -5.6435

Max Act: 4.5891. Min Act: -0.0000

Data Index: 707211 (The Pile)

Max Activating Token Index: 117

Text #9

Max Range: 5.6435. Min Range: -5.6435

Max Act: 4.7216. Min Act: -0.0000

Data Index: 1241871 (The Pile)

Max Activating Token Index: 277

Text #10

Max Range: 5.6435. Min Range: -5.6435

Max Act: 4.2500. Min Act: -0.0000

Data Index: 174942 (The Pile)

Max Activating Token Index: 580

Text #11

Max Range: 5.6435. Min Range: -5.6435

Max Act: 4.6354. Min Act: -0.0000

Data Index: 636787 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 5.6435. Min Range: -5.6435

Max Act: 4.4164. Min Act: -0.0000

Data Index: 1329239 (The Pile)

Max Activating Token Index: 369

Text #13

Max Range: 5.6435. Min Range: -5.6435

Max Act: 4.5659. Min Act: -0.0000

Data Index: 1870577 (The Pile)

Max Activating Token Index: 71

Text #14

Max Range: 5.6435. Min Range: -5.6435

Max Act: 4.5218. Min Act: -0.0000

Data Index: 514279 (The Pile)

Max Activating Token Index: 775

Text #15

Max Range: 5.6435. Min Range: -5.6435

Max Act: 4.5215. Min Act: -0.0000

Data Index: 674493 (The Pile)

Max Activating Token Index: 238

Text #16

Max Range: 5.6435. Min Range: -5.6435

Max Act: 4.4369. Min Act: -0.0000

Data Index: 549987 (The Pile)

Max Activating Token Index: 569

Text #17

Max Range: 5.6435. Min Range: -5.6435

Max Act: 4.2114. Min Act: -0.0000

Data Index: 223129 (The Pile)

Max Activating Token Index: 448

Text #18

Max Range: 5.6435. Min Range: -5.6435

Max Act: 4.5562. Min Act: -0.0000

Data Index: 1032013 (The Pile)

Max Activating Token Index: 624

Text #19

Max Range: 5.6435. Min Range: -5.6435

Max Act: 4.4145. Min Act: -0.0000

Data Index: 1752532 (The Pile)

Max Activating Token Index: 741