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

Dataset: The Pile

Neuron 2949 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: 1.0822. Min Range: -1.0822

Max Act: 1.0822. Min Act: 0.0000

Data Index: 1103696 (The Pile)

Max Activating Token Index: 389

Text #1

Max Range: 1.0822. Min Range: -1.0822

Max Act: 1.0424. Min Act: -0.0000

Data Index: 581382 (The Pile)

Max Activating Token Index: 355

Text #2

Max Range: 1.0822. Min Range: -1.0822

Max Act: 1.0500. Min Act: -0.0000

Data Index: 1502031 (The Pile)

Max Activating Token Index: 890

Text #3

Max Range: 1.0822. Min Range: -1.0822

Max Act: 1.0235. Min Act: -0.0000

Data Index: 401734 (The Pile)

Max Activating Token Index: 374

Text #4

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.9618. Min Act: -0.0000

Data Index: 1848831 (The Pile)

Max Activating Token Index: 423

Text #5

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.9411. Min Act: 0.0000

Data Index: 900389 (The Pile)

Max Activating Token Index: 978

Text #6

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.7998. Min Act: -0.0000

Data Index: 788913 (The Pile)

Max Activating Token Index: 978

Text #7

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.8957. Min Act: -0.0000

Data Index: 342646 (The Pile)

Max Activating Token Index: 893

Text #8

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.8272. Min Act: -0.0000

Data Index: 796064 (The Pile)

Max Activating Token Index: 548

Text #9

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.8133. Min Act: -0.0000

Data Index: 1229845 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.8207. Min Act: -0.0000

Data Index: 490351 (The Pile)

Max Activating Token Index: 823

Text #11

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.8410. Min Act: -0.0000

Data Index: 1789496 (The Pile)

Max Activating Token Index: 584

Text #12

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.8650. Min Act: 0.0000

Data Index: 1372351 (The Pile)

Max Activating Token Index: 998

Text #13

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.7608. Min Act: -0.0000

Data Index: 933728 (The Pile)

Max Activating Token Index: 805

Text #14

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1236791 (The Pile)

Max Activating Token Index: 646

Text #15

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1114023 (The Pile)

Max Activating Token Index: 432

Text #16

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1388231 (The Pile)

Max Activating Token Index: 127

Text #17

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1373502 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.7141. Min Act: -0.0000

Data Index: 14775 (The Pile)

Max Activating Token Index: 837

Text #19

Max Range: 1.0822. Min Range: -1.0822

Max Act: 0.6628. Min Act: -0.0000

Data Index: 108656 (The Pile)

Max Activating Token Index: 355