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

Dataset: The Pile

Neuron 1228 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: 0.4342. Min Range: -0.4342

Max Act: 0.4342. Min Act: -0.0000

Data Index: 1510505 (The Pile)

Max Activating Token Index: 843

Text #1

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1471987 (The Pile)

Max Activating Token Index: 52

Text #2

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1584928 (The Pile)

Max Activating Token Index: 49

Text #3

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3975. Min Act: -0.0000

Data Index: 987276 (The Pile)

Max Activating Token Index: 150

Text #4

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3667. Min Act: -0.0000

Data Index: 227058 (The Pile)

Max Activating Token Index: 648

Text #5

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3324. Min Act: -0.0000

Data Index: 274533 (The Pile)

Max Activating Token Index: 609

Text #6

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3197. Min Act: -0.0000

Data Index: 384266 (The Pile)

Max Activating Token Index: 89

Text #7

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1431668 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3688. Min Act: -0.0000

Data Index: 835097 (The Pile)

Max Activating Token Index: 846

Text #9

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1346784 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3664. Min Act: -0.0000

Data Index: 1876505 (The Pile)

Max Activating Token Index: 231

Text #11

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3870. Min Act: -0.0000

Data Index: 1988710 (The Pile)

Max Activating Token Index: 669

Text #12

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1988952 (The Pile)

Max Activating Token Index: 668

Text #13

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3607. Min Act: -0.0000

Data Index: 1233323 (The Pile)

Max Activating Token Index: 883

Text #14

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.2367. Min Act: -0.0000

Data Index: 784970 (The Pile)

Max Activating Token Index: 979

Text #15

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3568. Min Act: -0.0000

Data Index: 782344 (The Pile)

Max Activating Token Index: 569

Text #16

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3303. Min Act: -0.0000

Data Index: 326399 (The Pile)

Max Activating Token Index: 698

Text #17

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3274. Min Act: -0.0000

Data Index: 266459 (The Pile)

Max Activating Token Index: 982

Text #18

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3263. Min Act: -0.0000

Data Index: 1364816 (The Pile)

Max Activating Token Index: 41

Text #19

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1918007 (The Pile)

Max Activating Token Index: 669