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

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

Neuron 4247 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.3438. Min Act: -0.0000

Data Index: 1264527 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.3091. Min Act: -0.0000

Data Index: 379799 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2940. Min Act: -0.0001

Data Index: 1002639 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2966. Min Act: -0.0000

Data Index: 708878 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2969. Min Act: -0.0001

Data Index: 461874 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2838. Min Act: -0.0000

Data Index: 724564 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2665. Min Act: -0.0000

Data Index: 27408 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2501. Min Act: -0.0000

Data Index: 1139809 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2710. Min Act: -0.0000

Data Index: 418005 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2887. Min Act: -0.0000

Data Index: 243897 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2666. Min Act: -0.0000

Data Index: 161035 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2296. Min Act: -0.0000

Data Index: 949113 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2455. Min Act: -0.0000

Data Index: 151626 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2435. Min Act: -0.0001

Data Index: 591673 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1168831 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2285. Min Act: -0.0000

Data Index: 781899 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2307. Min Act: -0.0001

Data Index: 1090403 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2198. Min Act: -0.0000

Data Index: 13783 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2364. Min Act: -0.0000

Data Index: 372171 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 0.3438. Min Range: -0.3438

Max Act: 0.2162. Min Act: -0.0000

Data Index: 790992 (C4 (Web Text))

Max Activating Token Index: 883