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

Dataset: The Pile

Neuron 1937 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: 3.1594. Min Range: -3.1594

Max Act: 3.1594. Min Act: -0.0000

Data Index: 1588199 (The Pile)

Max Activating Token Index: 535

Text #1

Max Range: 3.1594. Min Range: -3.1594

Max Act: 2.2369. Min Act: -0.0000

Data Index: 1871132 (The Pile)

Max Activating Token Index: 119

Text #2

Max Range: 3.1594. Min Range: -3.1594

Max Act: 1.9513. Min Act: -0.0000

Data Index: 1772559 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 3.1594. Min Range: -3.1594

Max Act: 2.0301. Min Act: -0.0000

Data Index: 1483741 (The Pile)

Max Activating Token Index: 214

Text #4

Max Range: 3.1594. Min Range: -3.1594

Max Act: 1.7898. Min Act: -0.0000

Data Index: 374899 (The Pile)

Max Activating Token Index: 350

Text #5

Max Range: 3.1594. Min Range: -3.1594

Max Act: 1.6048. Min Act: -0.0000

Data Index: 1586276 (The Pile)

Max Activating Token Index: 292

Text #6

Max Range: 3.1594. Min Range: -3.1594

Max Act: 1.5520. Min Act: -0.0000

Data Index: 646853 (The Pile)

Max Activating Token Index: 208

Text #7

Max Range: 3.1594. Min Range: -3.1594

Max Act: 1.5184. Min Act: -0.0000

Data Index: 1248513 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 3.1594. Min Range: -3.1594

Max Act: 1.3228. Min Act: -0.0000

Data Index: 629219 (The Pile)

Max Activating Token Index: 340

Text #9

Max Range: 3.1594. Min Range: -3.1594

Max Act: 1.2830. Min Act: -0.0000

Data Index: 42699 (The Pile)

Max Activating Token Index: 403

Text #10

Max Range: 3.1594. Min Range: -3.1594

Max Act: 1.0178. Min Act: -0.0000

Data Index: 8521 (The Pile)

Max Activating Token Index: 849

Text #11

Max Range: 3.1594. Min Range: -3.1594

Max Act: 1.2823. Min Act: -0.0000

Data Index: 756193 (The Pile)

Max Activating Token Index: 885

Text #12

Max Range: 3.1594. Min Range: -3.1594

Max Act: 1.1767. Min Act: -0.0000

Data Index: 1385448 (The Pile)

Max Activating Token Index: 841

Text #13

Max Range: 3.1594. Min Range: -3.1594

Max Act: 1.2305. Min Act: -0.0000

Data Index: 211706 (The Pile)

Max Activating Token Index: 906

Text #14

Max Range: 3.1594. Min Range: -3.1594

Max Act: 1.2036. Min Act: 0.0000

Data Index: 503547 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 3.1594. Min Range: -3.1594

Max Act: 1.2267. Min Act: -0.0000

Data Index: 1651212 (The Pile)

Max Activating Token Index: 1008

Text #16

Max Range: 3.1594. Min Range: -3.1594

Max Act: 1.2930. Min Act: -0.0000

Data Index: 1461230 (The Pile)

Max Activating Token Index: 508

Text #17

Max Range: 3.1594. Min Range: -3.1594

Max Act: 1.0251. Min Act: -0.0000

Data Index: 35599 (The Pile)

Max Activating Token Index: 807

Text #18

Max Range: 3.1594. Min Range: -3.1594

Max Act: 1.0700. Min Act: -0.0000

Data Index: 1876120 (The Pile)

Max Activating Token Index: 558

Text #19

Max Range: 3.1594. Min Range: -3.1594

Max Act: 1.0999. Min Act: -0.0000

Data Index: 230865 (The Pile)

Max Activating Token Index: 964