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

Dataset: The Pile

Neuron 876 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: 3.1765. Min Range: -3.1765

Max Act: 3.1765. Min Act: -0.0000

Data Index: 158542 (The Pile)

Max Activating Token Index: 19

Text #1

Max Range: 3.1765. Min Range: -3.1765

Max Act: 3.1765. Min Act: -0.0000

Data Index: 964882 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 3.1765. Min Range: -3.1765

Max Act: 3.1448. Min Act: -0.0000

Data Index: 96781 (The Pile)

Max Activating Token Index: 17

Text #3

Max Range: 3.1765. Min Range: -3.1765

Max Act: 2.4981. Min Act: -0.0000

Data Index: 191633 (The Pile)

Max Activating Token Index: 967

Text #4

Max Range: 3.1765. Min Range: -3.1765

Max Act: 2.7354. Min Act: -0.0000

Data Index: 932822 (The Pile)

Max Activating Token Index: 1016

Text #5

Max Range: 3.1765. Min Range: -3.1765

Max Act: 2.9995. Min Act: -0.0000

Data Index: 1236883 (The Pile)

Max Activating Token Index: 16

Text #6

Max Range: 3.1765. Min Range: -3.1765

Max Act: 2.6912. Min Act: -0.0000

Data Index: 1501280 (The Pile)

Max Activating Token Index: 960

Text #7

Max Range: 3.1765. Min Range: -3.1765

Max Act: 2.3389. Min Act: -0.0000

Data Index: 924084 (The Pile)

Max Activating Token Index: 944

Text #8

Max Range: 3.1765. Min Range: -3.1765

Max Act: 2.6110. Min Act: -0.0000

Data Index: 223414 (The Pile)

Max Activating Token Index: 994

Text #9

Max Range: 3.1765. Min Range: -3.1765

Max Act: 2.4171. Min Act: -0.0000

Data Index: 1516037 (The Pile)

Max Activating Token Index: 839

Text #10

Max Range: 3.1765. Min Range: -3.1765

Max Act: 2.8064. Min Act: -0.0000

Data Index: 1629378 (The Pile)

Max Activating Token Index: 415

Text #11

Max Range: 3.1765. Min Range: -3.1765

Max Act: 2.7312. Min Act: -0.0000

Data Index: 107626 (The Pile)

Max Activating Token Index: 796

Text #12

Max Range: 3.1765. Min Range: -3.1765

Max Act: 2.7423. Min Act: -0.0000

Data Index: 1935105 (The Pile)

Max Activating Token Index: 547

Text #13

Max Range: 3.1765. Min Range: -3.1765

Max Act: 2.5245. Min Act: -0.0000

Data Index: 848342 (The Pile)

Max Activating Token Index: 949

Text #14

Max Range: 3.1765. Min Range: -3.1765

Max Act: 2.7933. Min Act: -0.0000

Data Index: 1219782 (The Pile)

Max Activating Token Index: 283

Text #15

Max Range: 3.1765. Min Range: -3.1765

Max Act: 2.7892. Min Act: -0.0000

Data Index: 1273246 (The Pile)

Max Activating Token Index: 472

Text #16

Max Range: 3.1765. Min Range: -3.1765

Max Act: 2.6360. Min Act: -0.0000

Data Index: 223703 (The Pile)

Max Activating Token Index: 352

Text #17

Max Range: 3.1765. Min Range: -3.1765

Max Act: 2.5319. Min Act: -0.0000

Data Index: 1328181 (The Pile)

Max Activating Token Index: 784

Text #18

Max Range: 3.1765. Min Range: -3.1765

Max Act: 2.5060. Min Act: -0.0000

Data Index: 215290 (The Pile)

Max Activating Token Index: 369

Text #19

Max Range: 3.1765. Min Range: -3.1765

Max Act: 2.2621. Min Act: -0.0000

Data Index: 1563092 (The Pile)

Max Activating Token Index: 41