Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1945 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.8557. Min Range: -4.8557

Max Act: 4.4261. Min Act: -0.0000

Data Index: 1029069 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 4.8557. Min Range: -4.8557

Max Act: 4.8557. Min Act: -0.0000

Data Index: 1148571 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 4.8557. Min Range: -4.8557

Max Act: 3.7192. Min Act: -0.0000

Data Index: 916021 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 4.8557. Min Range: -4.8557

Max Act: 3.2948. Min Act: -0.0000

Data Index: 705364 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 4.8557. Min Range: -4.8557

Max Act: 3.4015. Min Act: -0.0000

Data Index: 830297 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 4.8557. Min Range: -4.8557

Max Act: 3.2780. Min Act: -0.0000

Data Index: 450475 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 4.8557. Min Range: -4.8557

Max Act: 2.9344. Min Act: -0.0000

Data Index: 416605 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 4.8557. Min Range: -4.8557

Max Act: 3.2968. Min Act: -0.0000

Data Index: 649862 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 4.8557. Min Range: -4.8557

Max Act: 2.9478. Min Act: -0.0000

Data Index: 21132 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 4.8557. Min Range: -4.8557

Max Act: 3.0363. Min Act: -0.0000

Data Index: 549628 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 4.8557. Min Range: -4.8557

Max Act: 2.7255. Min Act: -0.0000

Data Index: 1343750 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 4.8557. Min Range: -4.8557

Max Act: 2.8671. Min Act: -0.0000

Data Index: 1059146 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 4.8557. Min Range: -4.8557

Max Act: 2.7044. Min Act: -0.0000

Data Index: 986977 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 4.8557. Min Range: -4.8557

Max Act: 2.0726. Min Act: -0.0000

Data Index: 117065 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 4.8557. Min Range: -4.8557

Max Act: 2.3659. Min Act: -0.0000

Data Index: 1189473 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 4.8557. Min Range: -4.8557

Max Act: 2.3320. Min Act: -0.0000

Data Index: 859913 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 4.8557. Min Range: -4.8557

Max Act: 2.3291. Min Act: -0.0000

Data Index: 1291065 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 4.8557. Min Range: -4.8557

Max Act: 2.6817. Min Act: -0.0000

Data Index: 253089 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 4.8557. Min Range: -4.8557

Max Act: 2.3687. Min Act: -0.0000

Data Index: 309619 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 4.8557. Min Range: -4.8557

Max Act: 2.5316. Min Act: -0.0000

Data Index: 340275 (C4 (Web Text))

Max Activating Token Index: 519