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

Dataset: The Pile

Neuron 2544 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: 0.6186. Min Range: -0.6186

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1646374 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.5472. Min Act: -0.0000

Data Index: 1854624 (The Pile)

Max Activating Token Index: 219

Text #2

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1456018 (The Pile)

Max Activating Token Index: 789

Text #3

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.5509. Min Act: -0.0000

Data Index: 882415 (The Pile)

Max Activating Token Index: 674

Text #4

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.5245. Min Act: -0.0000

Data Index: 777924 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1986785 (The Pile)

Max Activating Token Index: 417

Text #6

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1301972 (The Pile)

Max Activating Token Index: 588

Text #7

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1045756 (The Pile)

Max Activating Token Index: 556

Text #8

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4616. Min Act: -0.0000

Data Index: 630421 (The Pile)

Max Activating Token Index: 35

Text #9

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4939. Min Act: -0.0000

Data Index: 1078662 (The Pile)

Max Activating Token Index: 213

Text #10

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4676. Min Act: -0.0000

Data Index: 1055699 (The Pile)

Max Activating Token Index: 131

Text #11

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4428. Min Act: -0.0000

Data Index: 692741 (The Pile)

Max Activating Token Index: 257

Text #12

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4533. Min Act: -0.0000

Data Index: 512208 (The Pile)

Max Activating Token Index: 339

Text #13

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3712. Min Act: -0.0000

Data Index: 812394 (The Pile)

Max Activating Token Index: 723

Text #14

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4345. Min Act: -0.0000

Data Index: 560818 (The Pile)

Max Activating Token Index: 316

Text #15

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4224. Min Act: -0.0000

Data Index: 739717 (The Pile)

Max Activating Token Index: 566

Text #16

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4309. Min Act: -0.0000

Data Index: 398889 (The Pile)

Max Activating Token Index: 614

Text #17

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4596. Min Act: -0.0000

Data Index: 1517747 (The Pile)

Max Activating Token Index: 539

Text #18

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1780474 (The Pile)

Max Activating Token Index: 535

Text #19

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3968. Min Act: -0.0000

Data Index: 342466 (The Pile)

Max Activating Token Index: 537