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

Dataset: The Pile

Neuron 94 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1995. Min Range: -5.1995

Max Act: 5.1995. Min Act: -0.0000

Data Index: 841578 (The Pile)

Max Activating Token Index: 53

Text #1

Max Range: 5.1995. Min Range: -5.1995

Max Act: 5.1967. Min Act: -0.0000

Data Index: 1764198 (The Pile)

Max Activating Token Index: 52

Text #2

Max Range: 5.1995. Min Range: -5.1995

Max Act: 4.3406. Min Act: -0.0000

Data Index: 1143465 (The Pile)

Max Activating Token Index: 40

Text #3

Max Range: 5.1995. Min Range: -5.1995

Max Act: 4.1066. Min Act: -0.0000

Data Index: 616993 (The Pile)

Max Activating Token Index: 37

Text #4

Max Range: 5.1995. Min Range: -5.1995

Max Act: 3.5387. Min Act: -0.0000

Data Index: 447286 (The Pile)

Max Activating Token Index: 73

Text #5

Max Range: 5.1995. Min Range: -5.1995

Max Act: 3.6992. Min Act: -0.0000

Data Index: 684737 (The Pile)

Max Activating Token Index: 941

Text #6

Max Range: 5.1995. Min Range: -5.1995

Max Act: 1.5505. Min Act: -0.0000

Data Index: 456886 (The Pile)

Max Activating Token Index: 974

Text #7

Max Range: 5.1995. Min Range: -5.1995

Max Act: 1.5297. Min Act: -0.0000

Data Index: 980673 (The Pile)

Max Activating Token Index: 59

Text #8

Max Range: 5.1995. Min Range: -5.1995

Max Act: 1.6421. Min Act: -0.0000

Data Index: 432095 (The Pile)

Max Activating Token Index: 551

Text #9

Max Range: 5.1995. Min Range: -5.1995

Max Act: 1.4438. Min Act: -0.0000

Data Index: 648480 (The Pile)

Max Activating Token Index: 880

Text #10

Max Range: 5.1995. Min Range: -5.1995

Max Act: 1.5161. Min Act: -0.0000

Data Index: 1736200 (The Pile)

Max Activating Token Index: 491

Text #11

Max Range: 5.1995. Min Range: -5.1995

Max Act: 1.5488. Min Act: -0.0000

Data Index: 1917319 (The Pile)

Max Activating Token Index: 827

Text #12

Max Range: 5.1995. Min Range: -5.1995

Max Act: 1.5711. Min Act: -0.0000

Data Index: 299907 (The Pile)

Max Activating Token Index: 965

Text #13

Max Range: 5.1995. Min Range: -5.1995

Max Act: 1.5218. Min Act: -0.0000

Data Index: 864290 (The Pile)

Max Activating Token Index: 364

Text #14

Max Range: 5.1995. Min Range: -5.1995

Max Act: 1.5859. Min Act: -0.0000

Data Index: 342926 (The Pile)

Max Activating Token Index: 1002

Text #15

Max Range: 5.1995. Min Range: -5.1995

Max Act: 1.5483. Min Act: -0.0000

Data Index: 989537 (The Pile)

Max Activating Token Index: 783

Text #16

Max Range: 5.1995. Min Range: -5.1995

Max Act: 1.4407. Min Act: -0.0000

Data Index: 1324086 (The Pile)

Max Activating Token Index: 73

Text #17

Max Range: 5.1995. Min Range: -5.1995

Max Act: 1.3253. Min Act: -0.0000

Data Index: 1857209 (The Pile)

Max Activating Token Index: 909

Text #18

Max Range: 5.1995. Min Range: -5.1995

Max Act: 1.5444. Min Act: -0.0000

Data Index: 1909911 (The Pile)

Max Activating Token Index: 116

Text #19

Max Range: 5.1995. Min Range: -5.1995

Max Act: 1.5352. Min Act: -0.0000

Data Index: 1944459 (The Pile)

Max Activating Token Index: 255