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

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

Neuron 4019 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.7571. Min Act: -0.0000

Data Index: 48123 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.5788. Min Act: -0.0000

Data Index: 36450 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.6465. Min Act: -0.0001

Data Index: 1155700 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.5927. Min Act: -0.0001

Data Index: 489240 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.4733. Min Act: -0.0000

Data Index: 460727 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.4359. Min Act: -0.0000

Data Index: 959196 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.4776. Min Act: -0.0000

Data Index: 899329 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.4653. Min Act: -0.0000

Data Index: 984876 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.3288. Min Act: -0.0000

Data Index: 644822 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.4335. Min Act: -0.0001

Data Index: 58827 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.3311. Min Act: -0.0000

Data Index: 747862 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.2709. Min Act: -0.0000

Data Index: 864063 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.4529. Min Act: -0.0000

Data Index: 797408 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.2758. Min Act: -0.0001

Data Index: 1124066 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.3791. Min Act: -0.0000

Data Index: 1343291 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.3072. Min Act: -0.0000

Data Index: 6830 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.3079. Min Act: -0.0000

Data Index: 248335 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.1245. Min Act: -0.0000

Data Index: 467306 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.3228. Min Act: -0.0000

Data Index: 234611 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 1.7571. Min Range: -1.7571

Max Act: 1.2668. Min Act: -0.0000

Data Index: 139791 (C4 (Web Text))

Max Activating Token Index: 866