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

Dataset: The Pile

Neuron 3441 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.8188. Min Act: -0.0000

Data Index: 660889 (The Pile)

Max Activating Token Index: 272

Text #1

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.8172. Min Act: -0.0000

Data Index: 1194026 (The Pile)

Max Activating Token Index: 387

Text #2

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7732. Min Act: -0.0000

Data Index: 1409474 (The Pile)

Max Activating Token Index: 89

Text #3

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.8096. Min Act: -0.0000

Data Index: 998988 (The Pile)

Max Activating Token Index: 249

Text #4

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.8318. Min Act: -0.0000

Data Index: 850037 (The Pile)

Max Activating Token Index: 576

Text #5

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7581. Min Act: -0.0000

Data Index: 1002415 (The Pile)

Max Activating Token Index: 1006

Text #6

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1185561 (The Pile)

Max Activating Token Index: 579

Text #7

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7452. Min Act: -0.0000

Data Index: 1002156 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.8475. Min Act: -0.0000

Data Index: 1331800 (The Pile)

Max Activating Token Index: 828

Text #9

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7451. Min Act: -0.0000

Data Index: 460345 (The Pile)

Max Activating Token Index: 907

Text #10

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1017745 (The Pile)

Max Activating Token Index: 494

Text #11

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.6920. Min Act: -0.0000

Data Index: 419389 (The Pile)

Max Activating Token Index: 505

Text #12

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7360. Min Act: -0.0000

Data Index: 302730 (The Pile)

Max Activating Token Index: 140

Text #13

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7997. Min Act: -0.0000

Data Index: 594115 (The Pile)

Max Activating Token Index: 694

Text #14

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7511. Min Act: -0.0000

Data Index: 738932 (The Pile)

Max Activating Token Index: 386

Text #15

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1946427 (The Pile)

Max Activating Token Index: 625

Text #16

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7265. Min Act: -0.0000

Data Index: 1749584 (The Pile)

Max Activating Token Index: 275

Text #17

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1720429 (The Pile)

Max Activating Token Index: 733

Text #18

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.6725. Min Act: -0.0000

Data Index: 95036 (The Pile)

Max Activating Token Index: 1003

Text #19

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7337. Min Act: -0.0000

Data Index: 268740 (The Pile)

Max Activating Token Index: 202