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

Dataset: The Pile

Neuron 976 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: 1.6990. Min Range: -1.6990

Max Act: 1.6990. Min Act: -0.0000

Data Index: 1653831 (The Pile)

Max Activating Token Index: 154

Text #1

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.4833. Min Act: -0.0000

Data Index: 1518643 (The Pile)

Max Activating Token Index: 458

Text #2

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.4598. Min Act: -0.0000

Data Index: 538442 (The Pile)

Max Activating Token Index: 353

Text #3

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.4391. Min Act: -0.0000

Data Index: 1810822 (The Pile)

Max Activating Token Index: 361

Text #4

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.5398. Min Act: -0.0000

Data Index: 1015665 (The Pile)

Max Activating Token Index: 634

Text #5

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.3985. Min Act: -0.0000

Data Index: 1262072 (The Pile)

Max Activating Token Index: 466

Text #6

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.3875. Min Act: -0.0000

Data Index: 1934866 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.3750. Min Act: -0.0000

Data Index: 654409 (The Pile)

Max Activating Token Index: 567

Text #8

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.4658. Min Act: -0.0000

Data Index: 1042718 (The Pile)

Max Activating Token Index: 9

Text #9

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.3515. Min Act: -0.0000

Data Index: 1955483 (The Pile)

Max Activating Token Index: 491

Text #10

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.3442. Min Act: -0.0000

Data Index: 1962233 (The Pile)

Max Activating Token Index: 526

Text #11

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.3335. Min Act: -0.0000

Data Index: 151526 (The Pile)

Max Activating Token Index: 369

Text #12

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.2424. Min Act: -0.0000

Data Index: 26719 (The Pile)

Max Activating Token Index: 788

Text #13

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.3085. Min Act: -0.0000

Data Index: 1441220 (The Pile)

Max Activating Token Index: 586

Text #14

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.3042. Min Act: -0.0000

Data Index: 701258 (The Pile)

Max Activating Token Index: 827

Text #15

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.3000. Min Act: -0.0000

Data Index: 1428187 (The Pile)

Max Activating Token Index: 207

Text #16

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.3696. Min Act: -0.0000

Data Index: 699392 (The Pile)

Max Activating Token Index: 1020

Text #17

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.1432. Min Act: -0.0000

Data Index: 1931796 (The Pile)

Max Activating Token Index: 830

Text #18

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.2833. Min Act: -0.0000

Data Index: 1578566 (The Pile)

Max Activating Token Index: 1005

Text #19

Max Range: 1.6990. Min Range: -1.6990

Max Act: 1.2856. Min Act: -0.0000

Data Index: 1651523 (The Pile)

Max Activating Token Index: 399