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

Dataset: The Pile

Neuron 2513 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: 0.9163. Min Range: -0.9163

Max Act: 0.8968. Min Act: -0.0000

Data Index: 1038520 (The Pile)

Max Activating Token Index: 89

Text #1

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.9163. Min Act: -0.0000

Data Index: 872837 (The Pile)

Max Activating Token Index: 560

Text #2

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1619036 (The Pile)

Max Activating Token Index: 448

Text #3

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.8611. Min Act: -0.0000

Data Index: 123792 (The Pile)

Max Activating Token Index: 981

Text #4

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1837112 (The Pile)

Max Activating Token Index: 1018

Text #5

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7811. Min Act: -0.0000

Data Index: 226137 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.8792. Min Act: -0.0000

Data Index: 1383774 (The Pile)

Max Activating Token Index: 131

Text #7

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.8680. Min Act: -0.0000

Data Index: 1229443 (The Pile)

Max Activating Token Index: 25

Text #8

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.8163. Min Act: -0.0000

Data Index: 695265 (The Pile)

Max Activating Token Index: 302

Text #9

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1800761 (The Pile)

Max Activating Token Index: 172

Text #10

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.8207. Min Act: -0.0000

Data Index: 175436 (The Pile)

Max Activating Token Index: 348

Text #11

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.8534. Min Act: -0.0000

Data Index: 1302115 (The Pile)

Max Activating Token Index: 538

Text #12

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7766. Min Act: -0.0000

Data Index: 63840 (The Pile)

Max Activating Token Index: 533

Text #13

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1649556 (The Pile)

Max Activating Token Index: 482

Text #14

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7345. Min Act: -0.0000

Data Index: 1461014 (The Pile)

Max Activating Token Index: 9

Text #15

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7572. Min Act: -0.0000

Data Index: 1265809 (The Pile)

Max Activating Token Index: 838

Text #16

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7817. Min Act: -0.0000

Data Index: 168889 (The Pile)

Max Activating Token Index: 293

Text #17

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1517811 (The Pile)

Max Activating Token Index: 325

Text #18

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1221893 (The Pile)

Max Activating Token Index: 930

Text #19

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7400. Min Act: -0.0000

Data Index: 1393171 (The Pile)

Max Activating Token Index: 580