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

Dataset: The Pile

Neuron 3918 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.8716. Min Act: -0.0000

Data Index: 872311 (The Pile)

Max Activating Token Index: 730

Text #1

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.8846. Min Act: -0.0000

Data Index: 192419 (The Pile)

Max Activating Token Index: 135

Text #2

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.8116. Min Act: -0.0000

Data Index: 485638 (The Pile)

Max Activating Token Index: 121

Text #3

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7610. Min Act: -0.0000

Data Index: 696374 (The Pile)

Max Activating Token Index: 944

Text #4

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7816. Min Act: -0.0000

Data Index: 1096896 (The Pile)

Max Activating Token Index: 141

Text #5

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7284. Min Act: 0.0000

Data Index: 685614 (The Pile)

Max Activating Token Index: 407

Text #6

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7441. Min Act: -0.0000

Data Index: 1100193 (The Pile)

Max Activating Token Index: 146

Text #7

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7379. Min Act: -0.0000

Data Index: 1544841 (The Pile)

Max Activating Token Index: 68

Text #8

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7387. Min Act: -0.0000

Data Index: 726385 (The Pile)

Max Activating Token Index: 232

Text #9

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7061. Min Act: -0.0000

Data Index: 614412 (The Pile)

Max Activating Token Index: 469

Text #10

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7255. Min Act: -0.0000

Data Index: 554291 (The Pile)

Max Activating Token Index: 216

Text #11

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.6848. Min Act: -0.0000

Data Index: 346489 (The Pile)

Max Activating Token Index: 775

Text #12

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7213. Min Act: -0.0000

Data Index: 1925983 (The Pile)

Max Activating Token Index: 491

Text #13

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1619433 (The Pile)

Max Activating Token Index: 269

Text #14

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7185. Min Act: -0.0000

Data Index: 630757 (The Pile)

Max Activating Token Index: 588

Text #15

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1927564 (The Pile)

Max Activating Token Index: 343

Text #16

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7020. Min Act: -0.0000

Data Index: 1871394 (The Pile)

Max Activating Token Index: 826

Text #17

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.6651. Min Act: -0.0000

Data Index: 276416 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.6845. Min Act: -0.0000

Data Index: 1731494 (The Pile)

Max Activating Token Index: 963

Text #19

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1371196 (The Pile)

Max Activating Token Index: 602