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

Dataset: The Pile

Neuron 3243 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.5309. Min Act: -0.0000

Data Index: 1070971 (The Pile)

Max Activating Token Index: 92

Text #1

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1965254 (The Pile)

Max Activating Token Index: 369

Text #2

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1331119 (The Pile)

Max Activating Token Index: 78

Text #3

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4849. Min Act: -0.0000

Data Index: 338398 (The Pile)

Max Activating Token Index: 671

Text #4

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1466147 (The Pile)

Max Activating Token Index: 268

Text #5

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4415. Min Act: -0.0000

Data Index: 11167 (The Pile)

Max Activating Token Index: 277

Text #6

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4498. Min Act: -0.0000

Data Index: 570722 (The Pile)

Max Activating Token Index: 436

Text #7

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1952231 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4413. Min Act: -0.0000

Data Index: 490132 (The Pile)

Max Activating Token Index: 998

Text #9

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4079. Min Act: -0.0000

Data Index: 553805 (The Pile)

Max Activating Token Index: 474

Text #10

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4459. Min Act: -0.0000

Data Index: 521986 (The Pile)

Max Activating Token Index: 102

Text #11

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4313. Min Act: -0.0000

Data Index: 510436 (The Pile)

Max Activating Token Index: 1018

Text #12

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4321. Min Act: -0.0000

Data Index: 209251 (The Pile)

Max Activating Token Index: 215

Text #13

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4425. Min Act: -0.0000

Data Index: 287875 (The Pile)

Max Activating Token Index: 833

Text #14

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4358. Min Act: -0.0000

Data Index: 1981602 (The Pile)

Max Activating Token Index: 372

Text #15

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1440870 (The Pile)

Max Activating Token Index: 953

Text #16

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1172542 (The Pile)

Max Activating Token Index: 463

Text #17

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4254. Min Act: -0.0000

Data Index: 1778042 (The Pile)

Max Activating Token Index: 824

Text #18

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3971. Min Act: -0.0000

Data Index: 1367889 (The Pile)

Max Activating Token Index: 23

Text #19

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3972. Min Act: 0.0000

Data Index: 475216 (The Pile)

Max Activating Token Index: 554