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

Dataset: The Pile

Neuron 516 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.7203. Min Act: -0.0000

Data Index: 1307663 (The Pile)

Max Activating Token Index: 639

Text #1

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.5623. Min Act: -0.0000

Data Index: 282791 (The Pile)

Max Activating Token Index: 582

Text #2

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.5440. Min Act: -0.0000

Data Index: 1621341 (The Pile)

Max Activating Token Index: 333

Text #3

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.5405. Min Act: -0.0000

Data Index: 327440 (The Pile)

Max Activating Token Index: 622

Text #4

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.5221. Min Act: -0.0000

Data Index: 824648 (The Pile)

Max Activating Token Index: 191

Text #5

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.3993. Min Act: -0.0000

Data Index: 536549 (The Pile)

Max Activating Token Index: 244

Text #6

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.6654. Min Act: -0.0000

Data Index: 1537510 (The Pile)

Max Activating Token Index: 799

Text #7

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.3092. Min Act: -0.0000

Data Index: 1569627 (The Pile)

Max Activating Token Index: 341

Text #8

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.3175. Min Act: -0.0000

Data Index: 1263201 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.2334. Min Act: -0.0000

Data Index: 356716 (The Pile)

Max Activating Token Index: 318

Text #10

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.2240. Min Act: -0.0000

Data Index: 618358 (The Pile)

Max Activating Token Index: 907

Text #11

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.2085. Min Act: -0.0000

Data Index: 618538 (The Pile)

Max Activating Token Index: 217

Text #12

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.3061. Min Act: -0.0000

Data Index: 959179 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.2144. Min Act: -0.0000

Data Index: 701314 (The Pile)

Max Activating Token Index: 694

Text #14

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.1596. Min Act: -0.0000

Data Index: 324352 (The Pile)

Max Activating Token Index: 150

Text #15

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.2264. Min Act: -0.0000

Data Index: 893474 (The Pile)

Max Activating Token Index: 647

Text #16

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.0758. Min Act: -0.0000

Data Index: 26753 (The Pile)

Max Activating Token Index: 533

Text #17

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.1534. Min Act: -0.0000

Data Index: 1435488 (The Pile)

Max Activating Token Index: 457

Text #18

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.2073. Min Act: -0.0000

Data Index: 72258 (The Pile)

Max Activating Token Index: 144

Text #19

Max Range: 1.7203. Min Range: -1.7203

Max Act: 1.1681. Min Act: -0.0000

Data Index: 1274057 (The Pile)

Max Activating Token Index: 561