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

Dataset: The Pile

Neuron 3091 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: 1.1900. Min Range: -1.1900

Max Act: 1.1900. Min Act: -0.0000

Data Index: 1414689 (The Pile)

Max Activating Token Index: 773

Text #1

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.8872. Min Act: -0.0000

Data Index: 1468069 (The Pile)

Max Activating Token Index: 17

Text #2

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1099854 (The Pile)

Max Activating Token Index: 216

Text #3

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.8277. Min Act: -0.0000

Data Index: 378605 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.8986. Min Act: -0.0000

Data Index: 1911894 (The Pile)

Max Activating Token Index: 305

Text #5

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1217486 (The Pile)

Max Activating Token Index: 292

Text #6

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.8460. Min Act: -0.0000

Data Index: 211283 (The Pile)

Max Activating Token Index: 884

Text #7

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.8374. Min Act: -0.0000

Data Index: 114445 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.8084. Min Act: -0.0000

Data Index: 950228 (The Pile)

Max Activating Token Index: 402

Text #9

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.8302. Min Act: -0.0000

Data Index: 224721 (The Pile)

Max Activating Token Index: 59

Text #10

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.8362. Min Act: -0.0000

Data Index: 51011 (The Pile)

Max Activating Token Index: 909

Text #11

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.8015. Min Act: -0.0000

Data Index: 1741000 (The Pile)

Max Activating Token Index: 725

Text #12

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1352036 (The Pile)

Max Activating Token Index: 754

Text #13

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.8384. Min Act: -0.0000

Data Index: 50311 (The Pile)

Max Activating Token Index: 255

Text #14

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.8090. Min Act: -0.0000

Data Index: 1803896 (The Pile)

Max Activating Token Index: 638

Text #15

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.8085. Min Act: -0.0000

Data Index: 1683683 (The Pile)

Max Activating Token Index: 294

Text #16

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.8046. Min Act: -0.0000

Data Index: 337737 (The Pile)

Max Activating Token Index: 649

Text #17

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.7835. Min Act: -0.0000

Data Index: 87595 (The Pile)

Max Activating Token Index: 559

Text #18

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.8093. Min Act: -0.0000

Data Index: 1355239 (The Pile)

Max Activating Token Index: 366

Text #19

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1259588 (The Pile)

Max Activating Token Index: 766