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

Dataset: The Pile

Neuron 941 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5469. Min Act: -0.0000

Data Index: 428310 (The Pile)

Max Activating Token Index: 19

Text #1

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5438. Min Act: -0.0000

Data Index: 650406 (The Pile)

Max Activating Token Index: 516

Text #2

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5178. Min Act: -0.0000

Data Index: 908582 (The Pile)

Max Activating Token Index: 58

Text #3

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5384. Min Act: -0.0000

Data Index: 1294178 (The Pile)

Max Activating Token Index: 387

Text #4

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5388. Min Act: -0.0000

Data Index: 96144 (The Pile)

Max Activating Token Index: 279

Text #5

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5143. Min Act: -0.0000

Data Index: 667749 (The Pile)

Max Activating Token Index: 140

Text #6

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.4997. Min Act: -0.0000

Data Index: 1930733 (The Pile)

Max Activating Token Index: 345

Text #7

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5100. Min Act: -0.0000

Data Index: 369826 (The Pile)

Max Activating Token Index: 21

Text #8

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5257. Min Act: -0.0000

Data Index: 619168 (The Pile)

Max Activating Token Index: 486

Text #9

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1585308 (The Pile)

Max Activating Token Index: 126

Text #10

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5135. Min Act: -0.0000

Data Index: 616326 (The Pile)

Max Activating Token Index: 12

Text #11

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1845215 (The Pile)

Max Activating Token Index: 192

Text #12

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1573327 (The Pile)

Max Activating Token Index: 810

Text #13

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.4780. Min Act: -0.0000

Data Index: 27350 (The Pile)

Max Activating Token Index: 361

Text #14

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.4895. Min Act: -0.0000

Data Index: 458159 (The Pile)

Max Activating Token Index: 303

Text #15

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1216655 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5021. Min Act: -0.0000

Data Index: 997746 (The Pile)

Max Activating Token Index: 349

Text #17

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1483579 (The Pile)

Max Activating Token Index: 567

Text #18

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5036. Min Act: -0.0000

Data Index: 500460 (The Pile)

Max Activating Token Index: 192

Text #19

Max Range: 0.5469. Min Range: -0.5469

Max Act: 0.5062. Min Act: -0.0000

Data Index: 1679486 (The Pile)

Max Activating Token Index: 111