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

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

Neuron 160 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.3821. Min Act: -0.0001

Data Index: 383074 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.0711. Min Act: -0.0001

Data Index: 1233942 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 1.3821. Min Range: -1.3821

Max Act: 1.0253. Min Act: -0.0001

Data Index: 412192 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 1.3821. Min Range: -1.3821

Max Act: 0.9541. Min Act: -0.0001

Data Index: 155543 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 1.3821. Min Range: -1.3821

Max Act: 0.9460. Min Act: -0.0001

Data Index: 959927 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 1.3821. Min Range: -1.3821

Max Act: 0.9440. Min Act: -0.0001

Data Index: 1042516 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 1.3821. Min Range: -1.3821

Max Act: 0.9645. Min Act: -0.0001

Data Index: 1332243 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 1.3821. Min Range: -1.3821

Max Act: 0.8509. Min Act: -0.0001

Data Index: 382040 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 1.3821. Min Range: -1.3821

Max Act: 0.9604. Min Act: -0.0001

Data Index: 1072705 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 1.3821. Min Range: -1.3821

Max Act: 0.9019. Min Act: -0.0001

Data Index: 654667 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 1.3821. Min Range: -1.3821

Max Act: 0.9509. Min Act: -0.0001

Data Index: 95010 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 1.3821. Min Range: -1.3821

Max Act: 0.9506. Min Act: -0.0001

Data Index: 167417 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 1.3821. Min Range: -1.3821

Max Act: 0.9036. Min Act: -0.0001

Data Index: 356881 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 1.3821. Min Range: -1.3821

Max Act: 0.8645. Min Act: -0.0001

Data Index: 1052930 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 1.3821. Min Range: -1.3821

Max Act: 0.9108. Min Act: -0.0001

Data Index: 397371 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 1.3821. Min Range: -1.3821

Max Act: 0.8461. Min Act: -0.0001

Data Index: 581911 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 1.3821. Min Range: -1.3821

Max Act: 0.8030. Min Act: -0.0001

Data Index: 172334 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 1.3821. Min Range: -1.3821

Max Act: 0.8720. Min Act: -0.0001

Data Index: 1198710 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 1.3821. Min Range: -1.3821

Max Act: 0.8649. Min Act: -0.0001

Data Index: 885185 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 1.3821. Min Range: -1.3821

Max Act: 0.8084. Min Act: -0.0001

Data Index: 82755 (C4 (Web Text))

Max Activating Token Index: 333