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

Dataset: The Pile

Neuron 3363 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4070. Min Range: -1.4070

Max Act: 1.4070. Min Act: -0.0000

Data Index: 1928236 (The Pile)

Max Activating Token Index: 471

Text #1

Max Range: 1.4070. Min Range: -1.4070

Max Act: 1.3597. Min Act: -0.0000

Data Index: 1198321 (The Pile)

Max Activating Token Index: 253

Text #2

Max Range: 1.4070. Min Range: -1.4070

Max Act: 1.3461. Min Act: -0.0000

Data Index: 1475612 (The Pile)

Max Activating Token Index: 693

Text #3

Max Range: 1.4070. Min Range: -1.4070

Max Act: 1.3217. Min Act: -0.0000

Data Index: 1499626 (The Pile)

Max Activating Token Index: 377

Text #4

Max Range: 1.4070. Min Range: -1.4070

Max Act: 1.2122. Min Act: -0.0000

Data Index: 1359474 (The Pile)

Max Activating Token Index: 331

Text #5

Max Range: 1.4070. Min Range: -1.4070

Max Act: 1.1332. Min Act: -0.0000

Data Index: 187807 (The Pile)

Max Activating Token Index: 149

Text #6

Max Range: 1.4070. Min Range: -1.4070

Max Act: 1.1228. Min Act: -0.0000

Data Index: 494163 (The Pile)

Max Activating Token Index: 473

Text #7

Max Range: 1.4070. Min Range: -1.4070

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1504713 (The Pile)

Max Activating Token Index: 735

Text #8

Max Range: 1.4070. Min Range: -1.4070

Max Act: 1.1188. Min Act: -0.0000

Data Index: 1686937 (The Pile)

Max Activating Token Index: 136

Text #9

Max Range: 1.4070. Min Range: -1.4070

Max Act: 1.0991. Min Act: -0.0000

Data Index: 271358 (The Pile)

Max Activating Token Index: 590

Text #10

Max Range: 1.4070. Min Range: -1.4070

Max Act: 1.0950. Min Act: -0.0000

Data Index: 1317878 (The Pile)

Max Activating Token Index: 708

Text #11

Max Range: 1.4070. Min Range: -1.4070

Max Act: 1.0657. Min Act: -0.0000

Data Index: 1389300 (The Pile)

Max Activating Token Index: 155

Text #12

Max Range: 1.4070. Min Range: -1.4070

Max Act: 1.0504. Min Act: -0.0000

Data Index: 1331783 (The Pile)

Max Activating Token Index: 714

Text #13

Max Range: 1.4070. Min Range: -1.4070

Max Act: 1.1221. Min Act: -0.0000

Data Index: 1746034 (The Pile)

Max Activating Token Index: 36

Text #14

Max Range: 1.4070. Min Range: -1.4070

Max Act: 1.0446. Min Act: -0.0000

Data Index: 634016 (The Pile)

Max Activating Token Index: 707

Text #15

Max Range: 1.4070. Min Range: -1.4070

Max Act: 0.9756. Min Act: -0.0000

Data Index: 1408006 (The Pile)

Max Activating Token Index: 46

Text #16

Max Range: 1.4070. Min Range: -1.4070

Max Act: 1.0319. Min Act: -0.0000

Data Index: 603037 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 1.4070. Min Range: -1.4070

Max Act: 1.0241. Min Act: -0.0000

Data Index: 459573 (The Pile)

Max Activating Token Index: 462

Text #18

Max Range: 1.4070. Min Range: -1.4070

Max Act: 0.9557. Min Act: -0.0000

Data Index: 366568 (The Pile)

Max Activating Token Index: 467

Text #19

Max Range: 1.4070. Min Range: -1.4070

Max Act: 1.0141. Min Act: -0.0000

Data Index: 530637 (The Pile)

Max Activating Token Index: 884