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

Dataset: The Pile

Neuron 381 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: 0.3926. Min Range: -0.3926

Max Act: 0.3926. Min Act: -0.0000

Data Index: 359713 (The Pile)

Max Activating Token Index: 273

Text #1

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.3195. Min Act: -0.0000

Data Index: 396517 (The Pile)

Max Activating Token Index: 570

Text #2

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1095803 (The Pile)

Max Activating Token Index: 563

Text #3

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.3365. Min Act: -0.0000

Data Index: 310892 (The Pile)

Max Activating Token Index: 976

Text #4

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.3395. Min Act: -0.0000

Data Index: 767448 (The Pile)

Max Activating Token Index: 644

Text #5

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2602. Min Act: -0.0000

Data Index: 1980746 (The Pile)

Max Activating Token Index: 416

Text #6

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.3074. Min Act: -0.0000

Data Index: 385329 (The Pile)

Max Activating Token Index: 181

Text #7

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2775. Min Act: -0.0000

Data Index: 1367171 (The Pile)

Max Activating Token Index: 127

Text #8

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2828. Min Act: -0.0000

Data Index: 1106754 (The Pile)

Max Activating Token Index: 142

Text #9

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2521. Min Act: -0.0001

Data Index: 1203563 (The Pile)

Max Activating Token Index: 65

Text #10

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2081. Min Act: -0.0000

Data Index: 550013 (The Pile)

Max Activating Token Index: 13

Text #11

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2441. Min Act: -0.0000

Data Index: 165234 (The Pile)

Max Activating Token Index: 687

Text #12

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1624653 (The Pile)

Max Activating Token Index: 802

Text #13

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2479. Min Act: -0.0000

Data Index: 620316 (The Pile)

Max Activating Token Index: 73

Text #14

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2487. Min Act: -0.0000

Data Index: 263639 (The Pile)

Max Activating Token Index: 1019

Text #15

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2488. Min Act: -0.0000

Data Index: 578598 (The Pile)

Max Activating Token Index: 919

Text #16

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2417. Min Act: -0.0000

Data Index: 859142 (The Pile)

Max Activating Token Index: 35

Text #17

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1898005 (The Pile)

Max Activating Token Index: 734

Text #18

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2161. Min Act: -0.0000

Data Index: 606820 (The Pile)

Max Activating Token Index: 339

Text #19

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2400. Min Act: -0.0000

Data Index: 1493201 (The Pile)

Max Activating Token Index: 968