Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1173 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1495. Min Range: -1.1495

Max Act: 1.1495. Min Act: -0.0000

Data Index: 25806 (The Pile)

Max Activating Token Index: 65

Text #1

Max Range: 1.1495. Min Range: -1.1495

Max Act: 1.1020. Min Act: -0.0000

Data Index: 1902919 (The Pile)

Max Activating Token Index: 681

Text #2

Max Range: 1.1495. Min Range: -1.1495

Max Act: 1.0976. Min Act: -0.0000

Data Index: 1372191 (The Pile)

Max Activating Token Index: 401

Text #3

Max Range: 1.1495. Min Range: -1.1495

Max Act: 1.0576. Min Act: -0.0000

Data Index: 1863843 (The Pile)

Max Activating Token Index: 567

Text #4

Max Range: 1.1495. Min Range: -1.1495

Max Act: 1.0327. Min Act: -0.0000

Data Index: 1347283 (The Pile)

Max Activating Token Index: 723

Text #5

Max Range: 1.1495. Min Range: -1.1495

Max Act: 1.0690. Min Act: -0.0000

Data Index: 570425 (The Pile)

Max Activating Token Index: 162

Text #6

Max Range: 1.1495. Min Range: -1.1495

Max Act: 1.0189. Min Act: -0.0000

Data Index: 1230092 (The Pile)

Max Activating Token Index: 152

Text #7

Max Range: 1.1495. Min Range: -1.1495

Max Act: 1.0697. Min Act: -0.0000

Data Index: 646258 (The Pile)

Max Activating Token Index: 691

Text #8

Max Range: 1.1495. Min Range: -1.1495

Max Act: 1.0454. Min Act: -0.0000

Data Index: 799601 (The Pile)

Max Activating Token Index: 340

Text #9

Max Range: 1.1495. Min Range: -1.1495

Max Act: 1.0319. Min Act: -0.0000

Data Index: 654705 (The Pile)

Max Activating Token Index: 315

Text #10

Max Range: 1.1495. Min Range: -1.1495

Max Act: 1.0191. Min Act: -0.0000

Data Index: 1912297 (The Pile)

Max Activating Token Index: 403

Text #11

Max Range: 1.1495. Min Range: -1.1495

Max Act: 1.0656. Min Act: -0.0000

Data Index: 954544 (The Pile)

Max Activating Token Index: 879

Text #12

Max Range: 1.1495. Min Range: -1.1495

Max Act: 1.0061. Min Act: -0.0000

Data Index: 1369270 (The Pile)

Max Activating Token Index: 393

Text #13

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.9884. Min Act: -0.0000

Data Index: 1418442 (The Pile)

Max Activating Token Index: 642

Text #14

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.9890. Min Act: -0.0000

Data Index: 1006164 (The Pile)

Max Activating Token Index: 409

Text #15

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.9936. Min Act: -0.0000

Data Index: 219504 (The Pile)

Max Activating Token Index: 537

Text #16

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.9929. Min Act: -0.0000

Data Index: 204716 (The Pile)

Max Activating Token Index: 189

Text #17

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.9758. Min Act: -0.0000

Data Index: 914579 (The Pile)

Max Activating Token Index: 321

Text #18

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.9155. Min Act: -0.0000

Data Index: 892619 (The Pile)

Max Activating Token Index: 959

Text #19

Max Range: 1.1495. Min Range: -1.1495

Max Act: 0.9904. Min Act: -0.0000

Data Index: 487555 (The Pile)

Max Activating Token Index: 450