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

Dataset: The Pile

Neuron 1768 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1207461 (The Pile)

Max Activating Token Index: 840

Text #1

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5826. Min Act: -0.0000

Data Index: 696510 (The Pile)

Max Activating Token Index: 774

Text #2

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.6119. Min Act: -0.0000

Data Index: 677271 (The Pile)

Max Activating Token Index: 215

Text #3

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.6050. Min Act: -0.0000

Data Index: 1295567 (The Pile)

Max Activating Token Index: 388

Text #4

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5328. Min Act: -0.0000

Data Index: 204253 (The Pile)

Max Activating Token Index: 334

Text #5

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1210486 (The Pile)

Max Activating Token Index: 574

Text #6

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.4780. Min Act: -0.0000

Data Index: 1293310 (The Pile)

Max Activating Token Index: 794

Text #7

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5355. Min Act: -0.0000

Data Index: 372774 (The Pile)

Max Activating Token Index: 141

Text #8

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1788394 (The Pile)

Max Activating Token Index: 370

Text #9

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.4995. Min Act: -0.0000

Data Index: 509085 (The Pile)

Max Activating Token Index: 615

Text #10

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5641. Min Act: -0.0000

Data Index: 765569 (The Pile)

Max Activating Token Index: 735

Text #11

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1476568 (The Pile)

Max Activating Token Index: 582

Text #12

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1023782 (The Pile)

Max Activating Token Index: 691

Text #13

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1536361 (The Pile)

Max Activating Token Index: 470

Text #14

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1493109 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.3966. Min Act: -0.0000

Data Index: 49970 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.4635. Min Act: -0.0000

Data Index: 642769 (The Pile)

Max Activating Token Index: 163

Text #17

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.4725. Min Act: -0.0000

Data Index: 1971439 (The Pile)

Max Activating Token Index: 366

Text #18

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1962993 (The Pile)

Max Activating Token Index: 428

Text #19

Max Range: 0.6358. Min Range: -0.6358

Max Act: 0.4278. Min Act: -0.0000

Data Index: 977009 (The Pile)

Max Activating Token Index: 261