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

Dataset: The Pile

Neuron 25 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: 0.7954. Min Range: -0.7954

Max Act: 0.7954. Min Act: -0.0000

Data Index: 152554 (The Pile)

Max Activating Token Index: 215

Text #1

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.7471. Min Act: -0.0000

Data Index: 208084 (The Pile)

Max Activating Token Index: 931

Text #2

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1172987 (The Pile)

Max Activating Token Index: 894

Text #3

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.7308. Min Act: -0.0000

Data Index: 339030 (The Pile)

Max Activating Token Index: 494

Text #4

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.7704. Min Act: -0.0000

Data Index: 1359113 (The Pile)

Max Activating Token Index: 447

Text #5

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1771759 (The Pile)

Max Activating Token Index: 542

Text #6

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1371823 (The Pile)

Max Activating Token Index: 414

Text #7

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.7427. Min Act: -0.0000

Data Index: 496032 (The Pile)

Max Activating Token Index: 393

Text #8

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1644909 (The Pile)

Max Activating Token Index: 621

Text #9

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6816. Min Act: -0.0000

Data Index: 473118 (The Pile)

Max Activating Token Index: 879

Text #10

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6550. Min Act: -0.0000

Data Index: 1615000 (The Pile)

Max Activating Token Index: 474

Text #11

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6940. Min Act: -0.0000

Data Index: 353268 (The Pile)

Max Activating Token Index: 148

Text #12

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6948. Min Act: -0.0000

Data Index: 749733 (The Pile)

Max Activating Token Index: 674

Text #13

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6646. Min Act: -0.0000

Data Index: 182504 (The Pile)

Max Activating Token Index: 379

Text #14

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6866. Min Act: -0.0000

Data Index: 703832 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6800. Min Act: -0.0000

Data Index: 1309480 (The Pile)

Max Activating Token Index: 27

Text #16

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6374. Min Act: -0.0000

Data Index: 728110 (The Pile)

Max Activating Token Index: 585

Text #17

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6584. Min Act: -0.0000

Data Index: 396502 (The Pile)

Max Activating Token Index: 252

Text #18

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6995. Min Act: -0.0000

Data Index: 76810 (The Pile)

Max Activating Token Index: 273

Text #19

Max Range: 0.7954. Min Range: -0.7954

Max Act: 0.6956. Min Act: -0.0000

Data Index: 757237 (The Pile)

Max Activating Token Index: 929