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

Dataset: The Pile

Neuron 965 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: 3.6446. Min Range: -3.6446

Max Act: 3.6446. Min Act: -0.0000

Data Index: 1197830 (The Pile)

Max Activating Token Index: 85

Text #1

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.4098. Min Act: -0.0000

Data Index: 83950 (The Pile)

Max Activating Token Index: 46

Text #2

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.3586. Min Act: -0.0000

Data Index: 1803798 (The Pile)

Max Activating Token Index: 61

Text #3

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.2061. Min Act: -0.0000

Data Index: 1890418 (The Pile)

Max Activating Token Index: 167

Text #4

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.3475. Min Act: -0.0000

Data Index: 1118655 (The Pile)

Max Activating Token Index: 931

Text #5

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.4266. Min Act: -0.0000

Data Index: 1663099 (The Pile)

Max Activating Token Index: 124

Text #6

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.2704. Min Act: -0.0000

Data Index: 1667689 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.4021. Min Act: -0.0000

Data Index: 1423903 (The Pile)

Max Activating Token Index: 651

Text #8

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.2543. Min Act: -0.0000

Data Index: 717340 (The Pile)

Max Activating Token Index: 276

Text #9

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.3963. Min Act: -0.0000

Data Index: 900690 (The Pile)

Max Activating Token Index: 32

Text #10

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.3959. Min Act: -0.0000

Data Index: 101553 (The Pile)

Max Activating Token Index: 949

Text #11

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.2291. Min Act: -0.0000

Data Index: 1955190 (The Pile)

Max Activating Token Index: 874

Text #12

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.2072. Min Act: -0.0000

Data Index: 1947775 (The Pile)

Max Activating Token Index: 188

Text #13

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.3520. Min Act: -0.0000

Data Index: 540727 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.1851. Min Act: -0.0000

Data Index: 1475220 (The Pile)

Max Activating Token Index: 148

Text #15

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.0075. Min Act: -0.0000

Data Index: 517502 (The Pile)

Max Activating Token Index: 978

Text #16

Max Range: 3.6446. Min Range: -3.6446

Max Act: 2.9593. Min Act: -0.0000

Data Index: 1638474 (The Pile)

Max Activating Token Index: 501

Text #17

Max Range: 3.6446. Min Range: -3.6446

Max Act: 2.9342. Min Act: -0.0000

Data Index: 637004 (The Pile)

Max Activating Token Index: 345

Text #18

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.0600. Min Act: -0.0000

Data Index: 1821645 (The Pile)

Max Activating Token Index: 564

Text #19

Max Range: 3.6446. Min Range: -3.6446

Max Act: 2.9159. Min Act: -0.0000

Data Index: 352253 (The Pile)

Max Activating Token Index: 743