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

Dataset: The Pile

Neuron 2744 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: 0.7388. Min Range: -0.7388

Max Act: 0.7388. Min Act: -0.0000

Data Index: 1419457 (The Pile)

Max Activating Token Index: 719

Text #1

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.7104. Min Act: -0.0000

Data Index: 77107 (The Pile)

Max Activating Token Index: 524

Text #2

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1142500 (The Pile)

Max Activating Token Index: 756

Text #3

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1114439 (The Pile)

Max Activating Token Index: 211

Text #4

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6419. Min Act: -0.0000

Data Index: 408837 (The Pile)

Max Activating Token Index: 639

Text #5

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6788. Min Act: -0.0000

Data Index: 663857 (The Pile)

Max Activating Token Index: 525

Text #6

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1749986 (The Pile)

Max Activating Token Index: 868

Text #7

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5954. Min Act: -0.0000

Data Index: 1447675 (The Pile)

Max Activating Token Index: 837

Text #8

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6304. Min Act: -0.0000

Data Index: 827940 (The Pile)

Max Activating Token Index: 789

Text #9

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1518459 (The Pile)

Max Activating Token Index: 977

Text #10

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6517. Min Act: -0.0000

Data Index: 939510 (The Pile)

Max Activating Token Index: 774

Text #11

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6408. Min Act: -0.0000

Data Index: 1376027 (The Pile)

Max Activating Token Index: 309

Text #12

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6016. Min Act: -0.0000

Data Index: 88426 (The Pile)

Max Activating Token Index: 611

Text #13

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6319. Min Act: -0.0000

Data Index: 807113 (The Pile)

Max Activating Token Index: 642

Text #14

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6566. Min Act: -0.0000

Data Index: 177093 (The Pile)

Max Activating Token Index: 616

Text #15

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6069. Min Act: -0.0000

Data Index: 379963 (The Pile)

Max Activating Token Index: 460

Text #16

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1892428 (The Pile)

Max Activating Token Index: 665

Text #17

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5870. Min Act: -0.0000

Data Index: 774285 (The Pile)

Max Activating Token Index: 560

Text #18

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5948. Min Act: -0.0000

Data Index: 1046699 (The Pile)

Max Activating Token Index: 167

Text #19

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5916. Min Act: -0.0000

Data Index: 277249 (The Pile)

Max Activating Token Index: 94