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

Dataset: The Pile

Neuron 2269 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0253. Min Range: -1.0253

Max Act: 1.0253. Min Act: -0.0000

Data Index: 221610 (The Pile)

Max Activating Token Index: 496

Text #1

Max Range: 1.0253. Min Range: -1.0253

Max Act: 1.0129. Min Act: -0.0000

Data Index: 425395 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.8881. Min Act: -0.0000

Data Index: 270390 (The Pile)

Max Activating Token Index: 245

Text #3

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.9337. Min Act: -0.0000

Data Index: 1045956 (The Pile)

Max Activating Token Index: 425

Text #4

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7875. Min Act: -0.0000

Data Index: 1327183 (The Pile)

Max Activating Token Index: 870

Text #5

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1102374 (The Pile)

Max Activating Token Index: 133

Text #6

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.8100. Min Act: -0.0000

Data Index: 810258 (The Pile)

Max Activating Token Index: 315

Text #7

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1738963 (The Pile)

Max Activating Token Index: 528

Text #8

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.8088. Min Act: -0.0000

Data Index: 1015001 (The Pile)

Max Activating Token Index: 338

Text #9

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.8327. Min Act: -0.0000

Data Index: 528553 (The Pile)

Max Activating Token Index: 119

Text #10

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1203746 (The Pile)

Max Activating Token Index: 948

Text #11

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7772. Min Act: -0.0000

Data Index: 214658 (The Pile)

Max Activating Token Index: 428

Text #12

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7992. Min Act: -0.0000

Data Index: 1141947 (The Pile)

Max Activating Token Index: 146

Text #13

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7558. Min Act: -0.0000

Data Index: 1238598 (The Pile)

Max Activating Token Index: 635

Text #14

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7473. Min Act: -0.0000

Data Index: 418173 (The Pile)

Max Activating Token Index: 127

Text #15

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7501. Min Act: -0.0000

Data Index: 249508 (The Pile)

Max Activating Token Index: 742

Text #16

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7273. Min Act: -0.0000

Data Index: 518909 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7347. Min Act: -0.0000

Data Index: 1825375 (The Pile)

Max Activating Token Index: 840

Text #18

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7638. Min Act: -0.0000

Data Index: 1323234 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 1.0253. Min Range: -1.0253

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1293644 (The Pile)

Max Activating Token Index: 43