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

Dataset: The Pile

Neuron 649 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: 1.5129. Min Range: -1.5129

Max Act: 1.5129. Min Act: -0.0000

Data Index: 947712 (The Pile)

Max Activating Token Index: 29

Text #1

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1935627 (The Pile)

Max Activating Token Index: 257

Text #2

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.9059. Min Act: -0.0000

Data Index: 1792588 (The Pile)

Max Activating Token Index: 530

Text #3

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.8404. Min Act: -0.0000

Data Index: 297372 (The Pile)

Max Activating Token Index: 264

Text #4

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.8723. Min Act: 0.0000

Data Index: 967441 (The Pile)

Max Activating Token Index: 290

Text #5

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.8413. Min Act: -0.0000

Data Index: 328881 (The Pile)

Max Activating Token Index: 701

Text #6

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.8139. Min Act: -0.0000

Data Index: 1326297 (The Pile)

Max Activating Token Index: 513

Text #7

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.8134. Min Act: -0.0000

Data Index: 598128 (The Pile)

Max Activating Token Index: 290

Text #8

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.7690. Min Act: -0.0000

Data Index: 877936 (The Pile)

Max Activating Token Index: 101

Text #9

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.7582. Min Act: -0.0000

Data Index: 1584832 (The Pile)

Max Activating Token Index: 902

Text #10

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1286501 (The Pile)

Max Activating Token Index: 607

Text #11

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.7888. Min Act: -0.0000

Data Index: 1273775 (The Pile)

Max Activating Token Index: 835

Text #12

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.8048. Min Act: -0.0000

Data Index: 213990 (The Pile)

Max Activating Token Index: 862

Text #13

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.7516. Min Act: -0.0000

Data Index: 560936 (The Pile)

Max Activating Token Index: 789

Text #14

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.7410. Min Act: -0.0000

Data Index: 390469 (The Pile)

Max Activating Token Index: 575

Text #15

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1636000 (The Pile)

Max Activating Token Index: 537

Text #16

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1371281 (The Pile)

Max Activating Token Index: 602

Text #17

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.7552. Min Act: -0.0000

Data Index: 145799 (The Pile)

Max Activating Token Index: 16

Text #18

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.6347. Min Act: -0.0000

Data Index: 889968 (The Pile)

Max Activating Token Index: 96

Text #19

Max Range: 1.5129. Min Range: -1.5129

Max Act: 0.6625. Min Act: -0.0000

Data Index: 738174 (The Pile)

Max Activating Token Index: 778