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

Dataset: The Pile

Neuron 608 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: 1.8432. Min Range: -1.8432

Max Act: 1.8432. Min Act: -0.0000

Data Index: 1006501 (The Pile)

Max Activating Token Index: 130

Text #1

Max Range: 1.8432. Min Range: -1.8432

Max Act: 1.6778. Min Act: -0.0000

Data Index: 1938132 (The Pile)

Max Activating Token Index: 774

Text #2

Max Range: 1.8432. Min Range: -1.8432

Max Act: 1.4090. Min Act: -0.0000

Data Index: 1348907 (The Pile)

Max Activating Token Index: 250

Text #3

Max Range: 1.8432. Min Range: -1.8432

Max Act: 1.4315. Min Act: -0.0000

Data Index: 944568 (The Pile)

Max Activating Token Index: 321

Text #4

Max Range: 1.8432. Min Range: -1.8432

Max Act: 1.4363. Min Act: -0.0000

Data Index: 494704 (The Pile)

Max Activating Token Index: 390

Text #5

Max Range: 1.8432. Min Range: -1.8432

Max Act: 1.4032. Min Act: -0.0000

Data Index: 951694 (The Pile)

Max Activating Token Index: 619

Text #6

Max Range: 1.8432. Min Range: -1.8432

Max Act: 1.1927. Min Act: -0.0000

Data Index: 613668 (The Pile)

Max Activating Token Index: 786

Text #7

Max Range: 1.8432. Min Range: -1.8432

Max Act: 1.3407. Min Act: -0.0000

Data Index: 1839909 (The Pile)

Max Activating Token Index: 769

Text #8

Max Range: 1.8432. Min Range: -1.8432

Max Act: 1.0571. Min Act: -0.0000

Data Index: 1808879 (The Pile)

Max Activating Token Index: 475

Text #9

Max Range: 1.8432. Min Range: -1.8432

Max Act: 1.4962. Min Act: -0.0000

Data Index: 1141863 (The Pile)

Max Activating Token Index: 608

Text #10

Max Range: 1.8432. Min Range: -1.8432

Max Act: 1.2751. Min Act: -0.0000

Data Index: 1107473 (The Pile)

Max Activating Token Index: 218

Text #11

Max Range: 1.8432. Min Range: -1.8432

Max Act: 1.4070. Min Act: -0.0000

Data Index: 1252053 (The Pile)

Max Activating Token Index: 331

Text #12

Max Range: 1.8432. Min Range: -1.8432

Max Act: 1.3436. Min Act: -0.0000

Data Index: 1015714 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 1.8432. Min Range: -1.8432

Max Act: 1.4198. Min Act: -0.0000

Data Index: 1453079 (The Pile)

Max Activating Token Index: 873

Text #14

Max Range: 1.8432. Min Range: -1.8432

Max Act: 1.2130. Min Act: -0.0000

Data Index: 1681518 (The Pile)

Max Activating Token Index: 377

Text #15

Max Range: 1.8432. Min Range: -1.8432

Max Act: 1.3312. Min Act: -0.0000

Data Index: 1157442 (The Pile)

Max Activating Token Index: 420

Text #16

Max Range: 1.8432. Min Range: -1.8432

Max Act: 1.4278. Min Act: -0.0000

Data Index: 906462 (The Pile)

Max Activating Token Index: 886

Text #17

Max Range: 1.8432. Min Range: -1.8432

Max Act: 1.1977. Min Act: -0.0000

Data Index: 1273752 (The Pile)

Max Activating Token Index: 465

Text #18

Max Range: 1.8432. Min Range: -1.8432

Max Act: 1.2805. Min Act: -0.0000

Data Index: 1345436 (The Pile)

Max Activating Token Index: 82

Text #19

Max Range: 1.8432. Min Range: -1.8432

Max Act: 1.1729. Min Act: -0.0000

Data Index: 227580 (The Pile)

Max Activating Token Index: 237