Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1392 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1899533 (The Pile)

Max Activating Token Index: 609

Text #1

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.8092. Min Act: -0.0000

Data Index: 1119903 (The Pile)

Max Activating Token Index: 446

Text #2

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.7723. Min Act: -0.0000

Data Index: 490078 (The Pile)

Max Activating Token Index: 336

Text #3

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.7720. Min Act: -0.0000

Data Index: 18026 (The Pile)

Max Activating Token Index: 983

Text #4

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1746971 (The Pile)

Max Activating Token Index: 741

Text #5

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.7457. Min Act: -0.0000

Data Index: 883366 (The Pile)

Max Activating Token Index: 584

Text #6

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.7092. Min Act: -0.0000

Data Index: 185232 (The Pile)

Max Activating Token Index: 433

Text #7

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1980745 (The Pile)

Max Activating Token Index: 158

Text #8

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.7257. Min Act: -0.0000

Data Index: 501439 (The Pile)

Max Activating Token Index: 100

Text #9

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.7048. Min Act: -0.0000

Data Index: 701300 (The Pile)

Max Activating Token Index: 121

Text #10

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.7060. Min Act: -0.0000

Data Index: 571904 (The Pile)

Max Activating Token Index: 535

Text #11

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6767. Min Act: -0.0000

Data Index: 1852921 (The Pile)

Max Activating Token Index: 284

Text #12

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6833. Min Act: -0.0000

Data Index: 1745874 (The Pile)

Max Activating Token Index: 668

Text #13

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6947. Min Act: -0.0000

Data Index: 535221 (The Pile)

Max Activating Token Index: 501

Text #14

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6472. Min Act: -0.0000

Data Index: 1152169 (The Pile)

Max Activating Token Index: 1009

Text #15

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6911. Min Act: -0.0000

Data Index: 1226948 (The Pile)

Max Activating Token Index: 59

Text #16

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6621. Min Act: -0.0000

Data Index: 100277 (The Pile)

Max Activating Token Index: 846

Text #17

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.7284. Min Act: -0.0000

Data Index: 187125 (The Pile)

Max Activating Token Index: 600

Text #18

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1215196 (The Pile)

Max Activating Token Index: 929

Text #19

Max Range: 0.8261. Min Range: -0.8261

Max Act: 0.6551. Min Act: -0.0000

Data Index: 360535 (The Pile)

Max Activating Token Index: 729