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

Dataset: The Pile

Neuron 2640 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: 0.7423. Min Range: -0.7423

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1655781 (The Pile)

Max Activating Token Index: 15

Text #1

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.7148. Min Act: -0.0000

Data Index: 457472 (The Pile)

Max Activating Token Index: 916

Text #2

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1746164 (The Pile)

Max Activating Token Index: 804

Text #3

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1663408 (The Pile)

Max Activating Token Index: 903

Text #4

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.6364. Min Act: -0.0000

Data Index: 688789 (The Pile)

Max Activating Token Index: 795

Text #5

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.7423. Min Act: -0.0000

Data Index: 758307 (The Pile)

Max Activating Token Index: 29

Text #6

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.6467. Min Act: -0.0000

Data Index: 798152 (The Pile)

Max Activating Token Index: 696

Text #7

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.6344. Min Act: -0.0000

Data Index: 1556884 (The Pile)

Max Activating Token Index: 708

Text #8

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.6072. Min Act: -0.0000

Data Index: 416842 (The Pile)

Max Activating Token Index: 993

Text #9

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.6668. Min Act: -0.0000

Data Index: 682162 (The Pile)

Max Activating Token Index: 602

Text #10

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.6602. Min Act: -0.0000

Data Index: 1222019 (The Pile)

Max Activating Token Index: 977

Text #11

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.5997. Min Act: -0.0000

Data Index: 347727 (The Pile)

Max Activating Token Index: 793

Text #12

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1294115 (The Pile)

Max Activating Token Index: 347

Text #13

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.6515. Min Act: -0.0000

Data Index: 808731 (The Pile)

Max Activating Token Index: 78

Text #14

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.5953. Min Act: -0.0000

Data Index: 761145 (The Pile)

Max Activating Token Index: 404

Text #15

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.6046. Min Act: -0.0000

Data Index: 987123 (The Pile)

Max Activating Token Index: 84

Text #16

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.6024. Min Act: -0.0000

Data Index: 567392 (The Pile)

Max Activating Token Index: 547

Text #17

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1826369 (The Pile)

Max Activating Token Index: 817

Text #18

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.6130. Min Act: -0.0000

Data Index: 1287171 (The Pile)

Max Activating Token Index: 143

Text #19

Max Range: 0.7423. Min Range: -0.7423

Max Act: 0.5650. Min Act: -0.0000

Data Index: 778247 (The Pile)

Max Activating Token Index: 838