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

Dataset: The Pile

Neuron 1928 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: 0.6436. Min Range: -0.6436

Max Act: 0.6108. Min Act: -0.0000

Data Index: 455368 (The Pile)

Max Activating Token Index: 660

Text #1

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1900037 (The Pile)

Max Activating Token Index: 869

Text #2

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5560. Min Act: -0.0000

Data Index: 675650 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.6133. Min Act: -0.0000

Data Index: 1513269 (The Pile)

Max Activating Token Index: 385

Text #4

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1103431 (The Pile)

Max Activating Token Index: 861

Text #5

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5461. Min Act: -0.0000

Data Index: 128595 (The Pile)

Max Activating Token Index: 919

Text #6

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5210. Min Act: -0.0000

Data Index: 1102009 (The Pile)

Max Activating Token Index: 429

Text #7

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5304. Min Act: -0.0001

Data Index: 1070247 (The Pile)

Max Activating Token Index: 746

Text #8

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1115177 (The Pile)

Max Activating Token Index: 657

Text #9

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1064035 (The Pile)

Max Activating Token Index: 507

Text #10

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5252. Min Act: -0.0000

Data Index: 1988668 (The Pile)

Max Activating Token Index: 722

Text #11

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5544. Min Act: -0.0000

Data Index: 691769 (The Pile)

Max Activating Token Index: 896

Text #12

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5296. Min Act: -0.0000

Data Index: 262799 (The Pile)

Max Activating Token Index: 965

Text #13

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5385. Min Act: -0.0000

Data Index: 1338147 (The Pile)

Max Activating Token Index: 966

Text #14

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5203. Min Act: -0.0000

Data Index: 1130958 (The Pile)

Max Activating Token Index: 288

Text #15

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5421. Min Act: -0.0001

Data Index: 1998480 (The Pile)

Max Activating Token Index: 569

Text #16

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5137. Min Act: -0.0000

Data Index: 361895 (The Pile)

Max Activating Token Index: 419

Text #17

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.4932. Min Act: -0.0000

Data Index: 838716 (The Pile)

Max Activating Token Index: 881

Text #18

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1197819 (The Pile)

Max Activating Token Index: 1017

Text #19

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.4831. Min Act: -0.0000

Data Index: 76077 (The Pile)

Max Activating Token Index: 594