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

Dataset: The Pile

Neuron 3992 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: 1.3470. Min Range: -1.3470

Max Act: 1.3470. Min Act: -0.0000

Data Index: 962612 (The Pile)

Max Activating Token Index: 73

Text #1

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.1105. Min Act: -0.0000

Data Index: 1753379 (The Pile)

Max Activating Token Index: 416

Text #2

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.9799. Min Act: -0.0000

Data Index: 1358998 (The Pile)

Max Activating Token Index: 574

Text #3

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1507731 (The Pile)

Max Activating Token Index: 401

Text #4

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.0015. Min Act: -0.0000

Data Index: 1956360 (The Pile)

Max Activating Token Index: 585

Text #5

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.9441. Min Act: -0.0000

Data Index: 997147 (The Pile)

Max Activating Token Index: 496

Text #6

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1085336 (The Pile)

Max Activating Token Index: 440

Text #7

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.9975. Min Act: -0.0000

Data Index: 358895 (The Pile)

Max Activating Token Index: 947

Text #8

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.9553. Min Act: -0.0000

Data Index: 1829108 (The Pile)

Max Activating Token Index: 591

Text #9

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.9509. Min Act: -0.0000

Data Index: 1646859 (The Pile)

Max Activating Token Index: 577

Text #10

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.9720. Min Act: -0.0000

Data Index: 223264 (The Pile)

Max Activating Token Index: 623

Text #11

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.9214. Min Act: -0.0000

Data Index: 996099 (The Pile)

Max Activating Token Index: 384

Text #12

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.9445. Min Act: -0.0000

Data Index: 31431 (The Pile)

Max Activating Token Index: 541

Text #13

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.8768. Min Act: -0.0000

Data Index: 1771506 (The Pile)

Max Activating Token Index: 827

Text #14

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1173521 (The Pile)

Max Activating Token Index: 581

Text #15

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.9507. Min Act: -0.0000

Data Index: 315384 (The Pile)

Max Activating Token Index: 266

Text #16

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.8997. Min Act: -0.0000

Data Index: 171381 (The Pile)

Max Activating Token Index: 501

Text #17

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.9099. Min Act: -0.0000

Data Index: 1211738 (The Pile)

Max Activating Token Index: 596

Text #18

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.8318. Min Act: -0.0000

Data Index: 1352249 (The Pile)

Max Activating Token Index: 321

Text #19

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.0057. Min Act: -0.0000

Data Index: 474640 (The Pile)

Max Activating Token Index: 97