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

Dataset: The Pile

Neuron 3784 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: 0.4313. Min Range: -0.4313

Max Act: 0.4313. Min Act: -0.0000

Data Index: 1822781 (The Pile)

Max Activating Token Index: 256

Text #1

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3978. Min Act: -0.0000

Data Index: 131540 (The Pile)

Max Activating Token Index: 827

Text #2

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3369. Min Act: -0.0000

Data Index: 566935 (The Pile)

Max Activating Token Index: 68

Text #3

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3336. Min Act: -0.0000

Data Index: 1549090 (The Pile)

Max Activating Token Index: 776

Text #4

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2970. Min Act: -0.0000

Data Index: 1293467 (The Pile)

Max Activating Token Index: 829

Text #5

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3016. Min Act: -0.0000

Data Index: 868446 (The Pile)

Max Activating Token Index: 22

Text #6

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2957. Min Act: -0.0000

Data Index: 1782272 (The Pile)

Max Activating Token Index: 434

Text #7

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1986765 (The Pile)

Max Activating Token Index: 242

Text #8

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2927. Min Act: -0.0000

Data Index: 1074560 (The Pile)

Max Activating Token Index: 47

Text #9

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2724. Min Act: -0.0000

Data Index: 1071935 (The Pile)

Max Activating Token Index: 222

Text #10

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2828. Min Act: -0.0000

Data Index: 929015 (The Pile)

Max Activating Token Index: 184

Text #11

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2681. Min Act: -0.0000

Data Index: 894456 (The Pile)

Max Activating Token Index: 26

Text #12

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2655. Min Act: -0.0000

Data Index: 1245465 (The Pile)

Max Activating Token Index: 11

Text #13

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2639. Min Act: -0.0000

Data Index: 999169 (The Pile)

Max Activating Token Index: 460

Text #14

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2729. Min Act: -0.0000

Data Index: 447972 (The Pile)

Max Activating Token Index: 361

Text #15

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2592. Min Act: -0.0000

Data Index: 542678 (The Pile)

Max Activating Token Index: 343

Text #16

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2725. Min Act: -0.0000

Data Index: 346626 (The Pile)

Max Activating Token Index: 514

Text #17

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2533. Min Act: -0.0000

Data Index: 920783 (The Pile)

Max Activating Token Index: 90

Text #18

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2495. Min Act: -0.0000

Data Index: 270003 (The Pile)

Max Activating Token Index: 788

Text #19

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2462. Min Act: -0.0000

Data Index: 299248 (The Pile)

Max Activating Token Index: 350