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

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

Neuron 755 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.4330. Min Act: -0.0001

Data Index: 1137458 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3755. Min Act: -0.0001

Data Index: 1303413 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3887. Min Act: -0.0001

Data Index: 386358 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3957. Min Act: -0.0001

Data Index: 1224391 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3622. Min Act: -0.0001

Data Index: 848278 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3886. Min Act: -0.0001

Data Index: 60644 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3783. Min Act: -0.0001

Data Index: 1016801 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3522. Min Act: -0.0001

Data Index: 223296 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3481. Min Act: -0.0001

Data Index: 497822 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3741. Min Act: -0.0001

Data Index: 859480 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3488. Min Act: -0.0001

Data Index: 604875 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3742. Min Act: -0.0001

Data Index: 1190092 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3374. Min Act: -0.0001

Data Index: 1278661 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3475. Min Act: -0.0001

Data Index: 35502 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3535. Min Act: -0.0001

Data Index: 1073516 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3417. Min Act: -0.0001

Data Index: 865594 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3316. Min Act: -0.0001

Data Index: 259970 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3420. Min Act: -0.0001

Data Index: 1621683 (Python Code)

Max Activating Token Index: 504

Text #18

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3110. Min Act: -0.0001

Data Index: 1000234 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.4330. Min Range: -0.4330

Max Act: 0.3366. Min Act: -0.0001

Data Index: 908143 (C4 (Web Text))

Max Activating Token Index: 406