Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 1888 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.8320. Min Act: -0.0001

Data Index: 1151261 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7985. Min Act: -0.0001

Data Index: 911713 (The Pile)

Max Activating Token Index: 796

Text #2

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7644. Min Act: -0.0001

Data Index: 1020103 (The Pile)

Max Activating Token Index: 923

Text #3

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.8024. Min Act: -0.0001

Data Index: 993033 (The Pile)

Max Activating Token Index: 619

Text #4

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.8006. Min Act: -0.0001

Data Index: 1133631 (The Pile)

Max Activating Token Index: 558

Text #5

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7738. Min Act: -0.0001

Data Index: 43699 (The Pile)

Max Activating Token Index: 766

Text #6

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7464. Min Act: -0.0001

Data Index: 657555 (The Pile)

Max Activating Token Index: 768

Text #7

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7936. Min Act: -0.0001

Data Index: 1156360 (The Pile)

Max Activating Token Index: 700

Text #8

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7659. Min Act: -0.0001

Data Index: 1856090 (The Pile)

Max Activating Token Index: 801

Text #9

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7866. Min Act: -0.0001

Data Index: 322450 (The Pile)

Max Activating Token Index: 199

Text #10

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7259. Min Act: -0.0001

Data Index: 887597 (The Pile)

Max Activating Token Index: 512

Text #11

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7501. Min Act: -0.0001

Data Index: 1754572 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7468. Min Act: -0.0001

Data Index: 1903439 (The Pile)

Max Activating Token Index: 1008

Text #13

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7191. Min Act: -0.0001

Data Index: 748245 (The Pile)

Max Activating Token Index: 704

Text #14

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7181. Min Act: -0.0001

Data Index: 336581 (The Pile)

Max Activating Token Index: 524

Text #15

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7386. Min Act: -0.0001

Data Index: 65317 (The Pile)

Max Activating Token Index: 788

Text #16

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7368. Min Act: -0.0001

Data Index: 435426 (The Pile)

Max Activating Token Index: 352

Text #17

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7099. Min Act: -0.0001

Data Index: 1316489 (The Pile)

Max Activating Token Index: 734

Text #18

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7366. Min Act: -0.0001

Data Index: 382596 (The Pile)

Max Activating Token Index: 994

Text #19

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7118. Min Act: -0.0001

Data Index: 861056 (The Pile)

Max Activating Token Index: 970