Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3002 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1131. Min Range: -1.1131

Max Act: 1.1131. Min Act: -0.0000

Data Index: 1458848 (The Pile)

Max Activating Token Index: 949

Text #1

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.9835. Min Act: -0.0000

Data Index: 790172 (The Pile)

Max Activating Token Index: 97

Text #2

Max Range: 1.1131. Min Range: -1.1131

Max Act: 1.0105. Min Act: -0.0000

Data Index: 1779137 (The Pile)

Max Activating Token Index: 240

Text #3

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.9271. Min Act: -0.0000

Data Index: 1034992 (The Pile)

Max Activating Token Index: 294

Text #4

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.8973. Min Act: -0.0000

Data Index: 1409607 (The Pile)

Max Activating Token Index: 481

Text #5

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.9630. Min Act: -0.0000

Data Index: 1757676 (The Pile)

Max Activating Token Index: 752

Text #6

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.9519. Min Act: -0.0000

Data Index: 1624564 (The Pile)

Max Activating Token Index: 563

Text #7

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.9550. Min Act: -0.0000

Data Index: 60506 (The Pile)

Max Activating Token Index: 491

Text #8

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.9581. Min Act: -0.0000

Data Index: 539295 (The Pile)

Max Activating Token Index: 370

Text #9

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.8544. Min Act: -0.0000

Data Index: 92804 (The Pile)

Max Activating Token Index: 267

Text #10

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1308680 (The Pile)

Max Activating Token Index: 664

Text #11

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.8474. Min Act: -0.0000

Data Index: 777415 (The Pile)

Max Activating Token Index: 404

Text #12

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.8567. Min Act: -0.0000

Data Index: 941004 (The Pile)

Max Activating Token Index: 1006

Text #13

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.8402. Min Act: -0.0000

Data Index: 1461713 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1363142 (The Pile)

Max Activating Token Index: 282

Text #15

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.8376. Min Act: -0.0000

Data Index: 728967 (The Pile)

Max Activating Token Index: 439

Text #16

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1284398 (The Pile)

Max Activating Token Index: 343

Text #17

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.7979. Min Act: -0.0000

Data Index: 897820 (The Pile)

Max Activating Token Index: 147

Text #18

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.8420. Min Act: -0.0000

Data Index: 960308 (The Pile)

Max Activating Token Index: 851

Text #19

Max Range: 1.1131. Min Range: -1.1131

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1014273 (The Pile)

Max Activating Token Index: 349