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

Dataset: The Pile

Neuron 1984 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.4857. Min Act: -0.0000

Data Index: 1119325 (The Pile)

Max Activating Token Index: 630

Text #1

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.3295. Min Act: -0.0000

Data Index: 107908 (The Pile)

Max Activating Token Index: 948

Text #2

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.2985. Min Act: -0.0000

Data Index: 112441 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.2773. Min Act: -0.0000

Data Index: 261302 (The Pile)

Max Activating Token Index: 378

Text #4

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.1501. Min Act: -0.0000

Data Index: 1110321 (The Pile)

Max Activating Token Index: 947

Text #5

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.2704. Min Act: -0.0000

Data Index: 1085734 (The Pile)

Max Activating Token Index: 564

Text #6

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.2707. Min Act: -0.0000

Data Index: 56160 (The Pile)

Max Activating Token Index: 862

Text #7

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.0687. Min Act: -0.0000

Data Index: 858786 (The Pile)

Max Activating Token Index: 964

Text #8

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.0528. Min Act: -0.0000

Data Index: 151451 (The Pile)

Max Activating Token Index: 1017

Text #9

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.1421. Min Act: -0.0000

Data Index: 638489 (The Pile)

Max Activating Token Index: 147

Text #10

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.0519. Min Act: -0.0000

Data Index: 1084563 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.1319. Min Act: -0.0000

Data Index: 1699911 (The Pile)

Max Activating Token Index: 499

Text #12

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.1118. Min Act: -0.0000

Data Index: 1551221 (The Pile)

Max Activating Token Index: 1019

Text #13

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.0831. Min Act: -0.0000

Data Index: 1282571 (The Pile)

Max Activating Token Index: 540

Text #14

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.0717. Min Act: -0.0000

Data Index: 1764280 (The Pile)

Max Activating Token Index: 10

Text #15

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.0622. Min Act: -0.0000

Data Index: 932309 (The Pile)

Max Activating Token Index: 476

Text #16

Max Range: 1.4857. Min Range: -1.4857

Max Act: 0.9811. Min Act: -0.0000

Data Index: 795480 (The Pile)

Max Activating Token Index: 142

Text #17

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.0537. Min Act: -0.0000

Data Index: 865049 (The Pile)

Max Activating Token Index: 309

Text #18

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.1107. Min Act: -0.0000

Data Index: 1432049 (The Pile)

Max Activating Token Index: 483

Text #19

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.0340. Min Act: -0.0000

Data Index: 897175 (The Pile)

Max Activating Token Index: 12