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

Dataset: The Pile

Neuron 3728 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: 1.1232. Min Range: -1.1232

Max Act: 1.0829. Min Act: -0.0000

Data Index: 790565 (The Pile)

Max Activating Token Index: 171

Text #1

Max Range: 1.1232. Min Range: -1.1232

Max Act: 1.1232. Min Act: -0.0000

Data Index: 663551 (The Pile)

Max Activating Token Index: 523

Text #2

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.9616. Min Act: -0.0000

Data Index: 188834 (The Pile)

Max Activating Token Index: 172

Text #3

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.9654. Min Act: -0.0000

Data Index: 1825722 (The Pile)

Max Activating Token Index: 522

Text #4

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.9375. Min Act: -0.0000

Data Index: 1188862 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8185. Min Act: -0.0000

Data Index: 672253 (The Pile)

Max Activating Token Index: 383

Text #6

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8321. Min Act: -0.0000

Data Index: 735255 (The Pile)

Max Activating Token Index: 474

Text #7

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8639. Min Act: -0.0000

Data Index: 505319 (The Pile)

Max Activating Token Index: 867

Text #8

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8860. Min Act: -0.0000

Data Index: 1416982 (The Pile)

Max Activating Token Index: 263

Text #9

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.7748. Min Act: -0.0000

Data Index: 425476 (The Pile)

Max Activating Token Index: 815

Text #10

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1015447 (The Pile)

Max Activating Token Index: 566

Text #11

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8183. Min Act: -0.0000

Data Index: 526467 (The Pile)

Max Activating Token Index: 800

Text #12

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8686. Min Act: -0.0000

Data Index: 712307 (The Pile)

Max Activating Token Index: 395

Text #13

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8752. Min Act: -0.0000

Data Index: 1265373 (The Pile)

Max Activating Token Index: 580

Text #14

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.9280. Min Act: -0.0000

Data Index: 14105 (The Pile)

Max Activating Token Index: 845

Text #15

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8016. Min Act: -0.0000

Data Index: 1581869 (The Pile)

Max Activating Token Index: 913

Text #16

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.7750. Min Act: -0.0000

Data Index: 305037 (The Pile)

Max Activating Token Index: 64

Text #17

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8130. Min Act: -0.0000

Data Index: 1206993 (The Pile)

Max Activating Token Index: 739

Text #18

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1365949 (The Pile)

Max Activating Token Index: 321

Text #19

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.7682. Min Act: -0.0000

Data Index: 903980 (The Pile)

Max Activating Token Index: 603