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

Dataset: The Pile

Neuron 2364 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: 0.8543. Min Range: -0.8543

Max Act: 0.8489. Min Act: -0.0000

Data Index: 894749 (The Pile)

Max Activating Token Index: 903

Text #1

Max Range: 0.8543. Min Range: -0.8543

Max Act: 0.8543. Min Act: 0.0000

Data Index: 701394 (The Pile)

Max Activating Token Index: 61

Text #2

Max Range: 0.8543. Min Range: -0.8543

Max Act: 0.7908. Min Act: -0.0000

Data Index: 542660 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 0.8543. Min Range: -0.8543

Max Act: 0.7157. Min Act: -0.0000

Data Index: 660585 (The Pile)

Max Activating Token Index: 583

Text #4

Max Range: 0.8543. Min Range: -0.8543

Max Act: 0.7580. Min Act: -0.0000

Data Index: 458091 (The Pile)

Max Activating Token Index: 556

Text #5

Max Range: 0.8543. Min Range: -0.8543

Max Act: 0.6896. Min Act: -0.0000

Data Index: 104218 (The Pile)

Max Activating Token Index: 545

Text #6

Max Range: 0.8543. Min Range: -0.8543

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1096114 (The Pile)

Max Activating Token Index: 993

Text #7

Max Range: 0.8543. Min Range: -0.8543

Max Act: 0.6963. Min Act: -0.0000

Data Index: 296980 (The Pile)

Max Activating Token Index: 594

Text #8

Max Range: 0.8543. Min Range: -0.8543

Max Act: 0.7328. Min Act: -0.0000

Data Index: 206703 (The Pile)

Max Activating Token Index: 245

Text #9

Max Range: 0.8543. Min Range: -0.8543

Max Act: 0.7176. Min Act: -0.0000

Data Index: 95274 (The Pile)

Max Activating Token Index: 396

Text #10

Max Range: 0.8543. Min Range: -0.8543

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1733477 (The Pile)

Max Activating Token Index: 169

Text #11

Max Range: 0.8543. Min Range: -0.8543

Max Act: 0.7175. Min Act: -0.0000

Data Index: 1268874 (The Pile)

Max Activating Token Index: 586

Text #12

Max Range: 0.8543. Min Range: -0.8543

Max Act: 0.6930. Min Act: -0.0000

Data Index: 305179 (The Pile)

Max Activating Token Index: 444

Text #13

Max Range: 0.8543. Min Range: -0.8543

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1721373 (The Pile)

Max Activating Token Index: 683

Text #14

Max Range: 0.8543. Min Range: -0.8543

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1010447 (The Pile)

Max Activating Token Index: 516

Text #15

Max Range: 0.8543. Min Range: -0.8543

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1930199 (The Pile)

Max Activating Token Index: 600

Text #16

Max Range: 0.8543. Min Range: -0.8543

Max Act: 0.6887. Min Act: -0.0000

Data Index: 1881947 (The Pile)

Max Activating Token Index: 244

Text #17

Max Range: 0.8543. Min Range: -0.8543

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1527767 (The Pile)

Max Activating Token Index: 50

Text #18

Max Range: 0.8543. Min Range: -0.8543

Max Act: 0.6716. Min Act: -0.0000

Data Index: 583591 (The Pile)

Max Activating Token Index: 205

Text #19

Max Range: 0.8543. Min Range: -0.8543

Max Act: 0.6560. Min Act: -0.0000

Data Index: 101575 (The Pile)

Max Activating Token Index: 536