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

Dataset: The Pile

Neuron 218 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.2671. Min Act: -0.0000

Data Index: 912314 (The Pile)

Max Activating Token Index: 688

Text #1

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.1265. Min Act: -0.0000

Data Index: 409136 (The Pile)

Max Activating Token Index: 943

Text #2

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.1719. Min Act: -0.0000

Data Index: 1016452 (The Pile)

Max Activating Token Index: 171

Text #3

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0995. Min Act: -0.0000

Data Index: 901182 (The Pile)

Max Activating Token Index: 215

Text #4

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0719. Min Act: -0.0000

Data Index: 63223 (The Pile)

Max Activating Token Index: 217

Text #5

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0661. Min Act: -0.0000

Data Index: 1206249 (The Pile)

Max Activating Token Index: 191

Text #6

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.1142. Min Act: -0.0000

Data Index: 1807941 (The Pile)

Max Activating Token Index: 413

Text #7

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0806. Min Act: -0.0000

Data Index: 1835415 (The Pile)

Max Activating Token Index: 616

Text #8

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0381. Min Act: -0.0000

Data Index: 1138787 (The Pile)

Max Activating Token Index: 261

Text #9

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0238. Min Act: -0.0000

Data Index: 50121 (The Pile)

Max Activating Token Index: 417

Text #10

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0514. Min Act: -0.0000

Data Index: 847602 (The Pile)

Max Activating Token Index: 606

Text #11

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9794. Min Act: -0.0000

Data Index: 1030972 (The Pile)

Max Activating Token Index: 350

Text #12

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9359. Min Act: -0.0000

Data Index: 836890 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9303. Min Act: -0.0000

Data Index: 678718 (The Pile)

Max Activating Token Index: 407

Text #14

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9137. Min Act: -0.0000

Data Index: 232937 (The Pile)

Max Activating Token Index: 148

Text #15

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1306002 (The Pile)

Max Activating Token Index: 569

Text #16

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9128. Min Act: -0.0000

Data Index: 1958420 (The Pile)

Max Activating Token Index: 632

Text #17

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9326. Min Act: -0.0000

Data Index: 211054 (The Pile)

Max Activating Token Index: 170

Text #18

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9380. Min Act: -0.0000

Data Index: 1757335 (The Pile)

Max Activating Token Index: 76

Text #19

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0320. Min Act: 0.0000

Data Index: 75012 (The Pile)

Max Activating Token Index: 879