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

Dataset: The Pile

Neuron 2481 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: 1.5118. Min Range: -1.5118

Max Act: 1.3270. Min Act: -0.0000

Data Index: 1040285 (The Pile)

Max Activating Token Index: 646

Text #1

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.5118. Min Act: -0.0000

Data Index: 277134 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.3870. Min Act: -0.0000

Data Index: 932006 (The Pile)

Max Activating Token Index: 667

Text #3

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.3897. Min Act: -0.0000

Data Index: 1259606 (The Pile)

Max Activating Token Index: 304

Text #4

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.5026. Min Act: -0.0000

Data Index: 186724 (The Pile)

Max Activating Token Index: 58

Text #5

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.3464. Min Act: -0.0000

Data Index: 1571395 (The Pile)

Max Activating Token Index: 699

Text #6

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.4411. Min Act: -0.0000

Data Index: 1579315 (The Pile)

Max Activating Token Index: 694

Text #7

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.2453. Min Act: -0.0000

Data Index: 699649 (The Pile)

Max Activating Token Index: 512

Text #8

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.2836. Min Act: -0.0000

Data Index: 471822 (The Pile)

Max Activating Token Index: 812

Text #9

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.2389. Min Act: 0.0000

Data Index: 191031 (The Pile)

Max Activating Token Index: 722

Text #10

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.2471. Min Act: -0.0000

Data Index: 445716 (The Pile)

Max Activating Token Index: 253

Text #11

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.2801. Min Act: -0.0000

Data Index: 1528981 (The Pile)

Max Activating Token Index: 51

Text #12

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.2484. Min Act: -0.0000

Data Index: 1377640 (The Pile)

Max Activating Token Index: 447

Text #13

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.1397. Min Act: -0.0000

Data Index: 1787398 (The Pile)

Max Activating Token Index: 621

Text #14

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.2711. Min Act: -0.0000

Data Index: 1128336 (The Pile)

Max Activating Token Index: 987

Text #15

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.1991. Min Act: -0.0000

Data Index: 437430 (The Pile)

Max Activating Token Index: 165

Text #16

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.0613. Min Act: -0.0000

Data Index: 1627577 (The Pile)

Max Activating Token Index: 945

Text #17

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.1442. Min Act: -0.0000

Data Index: 291406 (The Pile)

Max Activating Token Index: 200

Text #18

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.2082. Min Act: -0.0000

Data Index: 164523 (The Pile)

Max Activating Token Index: 389

Text #19

Max Range: 1.5118. Min Range: -1.5118

Max Act: 1.1760. Min Act: -0.0000

Data Index: 1751656 (The Pile)

Max Activating Token Index: 576