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

Dataset: The Pile

Neuron 3190 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1428321 (The Pile)

Max Activating Token Index: 561

Text #1

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1295. Min Act: -0.0000

Data Index: 625924 (The Pile)

Max Activating Token Index: 612

Text #2

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1262. Min Act: -0.0000

Data Index: 626171 (The Pile)

Max Activating Token Index: 660

Text #3

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1294. Min Act: -0.0000

Data Index: 921037 (The Pile)

Max Activating Token Index: 576

Text #4

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1272. Min Act: -0.0000

Data Index: 1603631 (The Pile)

Max Activating Token Index: 467

Text #5

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1182. Min Act: -0.0000

Data Index: 521519 (The Pile)

Max Activating Token Index: 815

Text #6

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1179. Min Act: -0.0000

Data Index: 614707 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1133. Min Act: -0.0000

Data Index: 34851 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1082. Min Act: -0.0000

Data Index: 1163315 (The Pile)

Max Activating Token Index: 661

Text #9

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1103. Min Act: -0.0000

Data Index: 1948619 (The Pile)

Max Activating Token Index: 630

Text #10

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1898164 (The Pile)

Max Activating Token Index: 912

Text #11

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1120. Min Act: -0.0000

Data Index: 3374 (The Pile)

Max Activating Token Index: 847

Text #12

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1143. Min Act: -0.0000

Data Index: 1250344 (The Pile)

Max Activating Token Index: 686

Text #13

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1257422 (The Pile)

Max Activating Token Index: 134

Text #14

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1588220 (The Pile)

Max Activating Token Index: 381

Text #15

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1110. Min Act: -0.0000

Data Index: 264237 (The Pile)

Max Activating Token Index: 374

Text #16

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1010. Min Act: -0.0000

Data Index: 1533438 (The Pile)

Max Activating Token Index: 686

Text #17

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1043. Min Act: -0.0000

Data Index: 142504 (The Pile)

Max Activating Token Index: 380

Text #18

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0958. Min Act: -0.0000

Data Index: 707333 (The Pile)

Max Activating Token Index: 699

Text #19

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0954. Min Act: -0.0000

Data Index: 29243 (The Pile)

Max Activating Token Index: 986