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

Dataset: The Pile

Neuron 1385 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1899531 (The Pile)

Max Activating Token Index: 904

Text #1

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1429. Min Act: -0.0000

Data Index: 1911886 (The Pile)

Max Activating Token Index: 813

Text #2

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1325. Min Act: -0.0000

Data Index: 982534 (The Pile)

Max Activating Token Index: 536

Text #3

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1803488 (The Pile)

Max Activating Token Index: 455

Text #4

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1260. Min Act: -0.0000

Data Index: 1962580 (The Pile)

Max Activating Token Index: 237

Text #5

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1209754 (The Pile)

Max Activating Token Index: 288

Text #6

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1182. Min Act: -0.0000

Data Index: 421182 (The Pile)

Max Activating Token Index: 553

Text #7

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1132. Min Act: -0.0000

Data Index: 1868139 (The Pile)

Max Activating Token Index: 668

Text #8

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1122. Min Act: -0.0000

Data Index: 1202499 (The Pile)

Max Activating Token Index: 382

Text #9

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1127. Min Act: -0.0000

Data Index: 638305 (The Pile)

Max Activating Token Index: 134

Text #10

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1212. Min Act: -0.0000

Data Index: 651066 (The Pile)

Max Activating Token Index: 208

Text #11

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1161860 (The Pile)

Max Activating Token Index: 381

Text #12

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1085. Min Act: -0.0000

Data Index: 122386 (The Pile)

Max Activating Token Index: 954

Text #13

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1230364 (The Pile)

Max Activating Token Index: 652

Text #14

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1116. Min Act: -0.0000

Data Index: 1860515 (The Pile)

Max Activating Token Index: 134

Text #15

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1029. Min Act: -0.0000

Data Index: 349454 (The Pile)

Max Activating Token Index: 663

Text #16

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1130762 (The Pile)

Max Activating Token Index: 60

Text #17

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1019. Min Act: -0.0000

Data Index: 45147 (The Pile)

Max Activating Token Index: 483

Text #18

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1059. Min Act: -0.0000

Data Index: 333402 (The Pile)

Max Activating Token Index: 660

Text #19

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1491260 (The Pile)

Max Activating Token Index: 662