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

Dataset: The Pile

Neuron 1076 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.6688. Min Act: -0.0000

Data Index: 1625250 (The Pile)

Max Activating Token Index: 490

Text #1

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.6863. Min Act: -0.0000

Data Index: 349372 (The Pile)

Max Activating Token Index: 214

Text #2

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.4571. Min Act: -0.0000

Data Index: 1181189 (The Pile)

Max Activating Token Index: 300

Text #3

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.4213. Min Act: -0.0000

Data Index: 1609916 (The Pile)

Max Activating Token Index: 126

Text #4

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.4722. Min Act: -0.0000

Data Index: 154512 (The Pile)

Max Activating Token Index: 576

Text #5

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.4296. Min Act: -0.0000

Data Index: 1615821 (The Pile)

Max Activating Token Index: 711

Text #6

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.4341. Min Act: -0.0000

Data Index: 892198 (The Pile)

Max Activating Token Index: 506

Text #7

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.2413. Min Act: -0.0000

Data Index: 1787627 (The Pile)

Max Activating Token Index: 135

Text #8

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.2519. Min Act: -0.0000

Data Index: 829534 (The Pile)

Max Activating Token Index: 384

Text #9

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.3843. Min Act: -0.0000

Data Index: 900452 (The Pile)

Max Activating Token Index: 162

Text #10

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.2548. Min Act: -0.0000

Data Index: 1952716 (The Pile)

Max Activating Token Index: 84

Text #11

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.3353. Min Act: -0.0000

Data Index: 708562 (The Pile)

Max Activating Token Index: 490

Text #12

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.3125. Min Act: -0.0000

Data Index: 1170087 (The Pile)

Max Activating Token Index: 948

Text #13

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.3757. Min Act: -0.0000

Data Index: 621966 (The Pile)

Max Activating Token Index: 52

Text #14

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.4164. Min Act: -0.0000

Data Index: 1896000 (The Pile)

Max Activating Token Index: 163

Text #15

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.2987. Min Act: -0.0000

Data Index: 1394079 (The Pile)

Max Activating Token Index: 609

Text #16

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.3087. Min Act: -0.0000

Data Index: 1423485 (The Pile)

Max Activating Token Index: 155

Text #17

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.3753. Min Act: -0.0000

Data Index: 1686183 (The Pile)

Max Activating Token Index: 999

Text #18

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.2754. Min Act: -0.0000

Data Index: 323579 (The Pile)

Max Activating Token Index: 907

Text #19

Max Range: 1.6863. Min Range: -1.6863

Max Act: 1.2336. Min Act: -0.0000

Data Index: 154746 (The Pile)

Max Activating Token Index: 476