Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2450 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.2416. Min Range: -5.2416

Max Act: 5.2416. Min Act: -0.0000

Data Index: 191007 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 5.2416. Min Range: -5.2416

Max Act: 4.5480. Min Act: -0.0001

Data Index: 100602 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 5.2416. Min Range: -5.2416

Max Act: 4.5362. Min Act: -0.0000

Data Index: 464469 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 5.2416. Min Range: -5.2416

Max Act: 4.4956. Min Act: -0.0001

Data Index: 345622 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 5.2416. Min Range: -5.2416

Max Act: 4.8185. Min Act: -0.0000

Data Index: 543329 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 5.2416. Min Range: -5.2416

Max Act: 4.7419. Min Act: -0.0001

Data Index: 1212212 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 5.2416. Min Range: -5.2416

Max Act: 4.3716. Min Act: -0.0000

Data Index: 698617 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 5.2416. Min Range: -5.2416

Max Act: 4.2120. Min Act: -0.0000

Data Index: 905878 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 5.2416. Min Range: -5.2416

Max Act: 4.3435. Min Act: -0.0000

Data Index: 170972 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 5.2416. Min Range: -5.2416

Max Act: 4.2697. Min Act: -0.0000

Data Index: 498363 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 5.2416. Min Range: -5.2416

Max Act: 3.9353. Min Act: -0.0000

Data Index: 379694 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 5.2416. Min Range: -5.2416

Max Act: 3.7294. Min Act: -0.0000

Data Index: 1106986 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 5.2416. Min Range: -5.2416

Max Act: 3.9938. Min Act: -0.0000

Data Index: 1322240 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 5.2416. Min Range: -5.2416

Max Act: 3.8527. Min Act: -0.0000

Data Index: 430360 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 5.2416. Min Range: -5.2416

Max Act: 3.7784. Min Act: -0.0000

Data Index: 1140063 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 5.2416. Min Range: -5.2416

Max Act: 4.0507. Min Act: -0.0000

Data Index: 1139197 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 5.2416. Min Range: -5.2416

Max Act: 3.7366. Min Act: -0.0001

Data Index: 1338287 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 5.2416. Min Range: -5.2416

Max Act: 3.7412. Min Act: -0.0000

Data Index: 309537 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 5.2416. Min Range: -5.2416

Max Act: 3.8893. Min Act: -0.0001

Data Index: 651379 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 5.2416. Min Range: -5.2416

Max Act: 3.8676. Min Act: -0.0001

Data Index: 579495 (C4 (Web Text))

Max Activating Token Index: 469