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

Dataset: The Pile

Neuron 1798 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4479. Min Range: -1.4479

Max Act: 1.4479. Min Act: -0.0000

Data Index: 381079 (The Pile)

Max Activating Token Index: 327

Text #1

Max Range: 1.4479. Min Range: -1.4479

Max Act: 1.2840. Min Act: -0.0000

Data Index: 878024 (The Pile)

Max Activating Token Index: 22

Text #2

Max Range: 1.4479. Min Range: -1.4479

Max Act: 1.4118. Min Act: -0.0000

Data Index: 1246499 (The Pile)

Max Activating Token Index: 981

Text #3

Max Range: 1.4479. Min Range: -1.4479

Max Act: 1.1449. Min Act: -0.0000

Data Index: 1239723 (The Pile)

Max Activating Token Index: 998

Text #4

Max Range: 1.4479. Min Range: -1.4479

Max Act: 1.1801. Min Act: -0.0000

Data Index: 1281800 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 1.4479. Min Range: -1.4479

Max Act: 1.0313. Min Act: -0.0000

Data Index: 944452 (The Pile)

Max Activating Token Index: 415

Text #6

Max Range: 1.4479. Min Range: -1.4479

Max Act: 1.1080. Min Act: -0.0000

Data Index: 741356 (The Pile)

Max Activating Token Index: 107

Text #7

Max Range: 1.4479. Min Range: -1.4479

Max Act: 1.0696. Min Act: -0.0000

Data Index: 1285651 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 1.4479. Min Range: -1.4479

Max Act: 1.1564. Min Act: -0.0000

Data Index: 494448 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 1.4479. Min Range: -1.4479

Max Act: 1.0785. Min Act: -0.0000

Data Index: 348285 (The Pile)

Max Activating Token Index: 780

Text #10

Max Range: 1.4479. Min Range: -1.4479

Max Act: 1.0360. Min Act: -0.0000

Data Index: 1146144 (The Pile)

Max Activating Token Index: 386

Text #11

Max Range: 1.4479. Min Range: -1.4479

Max Act: 1.0572. Min Act: -0.0000

Data Index: 166730 (The Pile)

Max Activating Token Index: 668

Text #12

Max Range: 1.4479. Min Range: -1.4479

Max Act: 1.0482. Min Act: -0.0000

Data Index: 1572232 (The Pile)

Max Activating Token Index: 404

Text #13

Max Range: 1.4479. Min Range: -1.4479

Max Act: 1.0887. Min Act: -0.0000

Data Index: 928403 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.9393. Min Act: -0.0000

Data Index: 205513 (The Pile)

Max Activating Token Index: 638

Text #15

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.9516. Min Act: -0.0000

Data Index: 1338066 (The Pile)

Max Activating Token Index: 175

Text #16

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.9842. Min Act: -0.0000

Data Index: 218069 (The Pile)

Max Activating Token Index: 246

Text #17

Max Range: 1.4479. Min Range: -1.4479

Max Act: 1.0136. Min Act: -0.0000

Data Index: 319641 (The Pile)

Max Activating Token Index: 219

Text #18

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.9765. Min Act: -0.0000

Data Index: 537423 (The Pile)

Max Activating Token Index: 137

Text #19

Max Range: 1.4479. Min Range: -1.4479

Max Act: 0.9222. Min Act: -0.0000

Data Index: 436030 (The Pile)

Max Activating Token Index: 341