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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2587 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3519. Min Range: -2.3519

Max Act: 2.3519. Min Act: -0.0000

Data Index: 478732 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 2.3519. Min Range: -2.3519

Max Act: 2.3318. Min Act: -0.0000

Data Index: 1210106 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 2.3519. Min Range: -2.3519

Max Act: 2.3164. Min Act: -0.0000

Data Index: 32010 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 2.3519. Min Range: -2.3519

Max Act: 2.0737. Min Act: -0.0000

Data Index: 1024298 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 2.3519. Min Range: -2.3519

Max Act: 2.0572. Min Act: -0.0000

Data Index: 849181 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 2.3519. Min Range: -2.3519

Max Act: 1.9993. Min Act: -0.0000

Data Index: 735193 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 2.3519. Min Range: -2.3519

Max Act: 2.1509. Min Act: -0.0001

Data Index: 357940 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 2.3519. Min Range: -2.3519

Max Act: 2.2374. Min Act: -0.0001

Data Index: 1022074 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 2.3519. Min Range: -2.3519

Max Act: 2.0035. Min Act: -0.0000

Data Index: 358969 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 2.3519. Min Range: -2.3519

Max Act: 2.2002. Min Act: -0.0000

Data Index: 1150776 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 2.3519. Min Range: -2.3519

Max Act: 2.0843. Min Act: -0.0000

Data Index: 914510 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 2.3519. Min Range: -2.3519

Max Act: 2.1715. Min Act: -0.0000

Data Index: 1297614 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 2.3519. Min Range: -2.3519

Max Act: 2.0529. Min Act: -0.0000

Data Index: 61703 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 2.3519. Min Range: -2.3519

Max Act: 2.0337. Min Act: -0.0001

Data Index: 673395 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 2.3519. Min Range: -2.3519

Max Act: 1.9838. Min Act: -0.0001

Data Index: 551647 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 2.3519. Min Range: -2.3519

Max Act: 1.9272. Min Act: -0.0001

Data Index: 947316 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 2.3519. Min Range: -2.3519

Max Act: 2.0826. Min Act: -0.0000

Data Index: 693807 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 2.3519. Min Range: -2.3519

Max Act: 1.9506. Min Act: -0.0001

Data Index: 676116 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 2.3519. Min Range: -2.3519

Max Act: 1.9588. Min Act: -0.0000

Data Index: 1046550 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 2.3519. Min Range: -2.3519

Max Act: 1.9525. Min Act: -0.0000

Data Index: 1211555 (C4 (Web Text))

Max Activating Token Index: 684