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

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

Neuron 3109 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: 1.8701. Min Range: -1.8701

Max Act: 1.8534. Min Act: -0.0001

Data Index: 472383 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 1.8701. Min Range: -1.8701

Max Act: 1.8701. Min Act: -0.0001

Data Index: 1105650 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 1.8701. Min Range: -1.8701

Max Act: 1.8257. Min Act: -0.0001

Data Index: 969802 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 1.8701. Min Range: -1.8701

Max Act: 1.6738. Min Act: -0.0001

Data Index: 671977 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 1.8701. Min Range: -1.8701

Max Act: 1.8398. Min Act: -0.0001

Data Index: 879919 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 1.8701. Min Range: -1.8701

Max Act: 1.5901. Min Act: -0.0001

Data Index: 333667 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 1.8701. Min Range: -1.8701

Max Act: 1.5590. Min Act: -0.0001

Data Index: 46032 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 1.8701. Min Range: -1.8701

Max Act: 1.5523. Min Act: -0.0001

Data Index: 388758 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 1.8701. Min Range: -1.8701

Max Act: 1.5862. Min Act: -0.0001

Data Index: 515484 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 1.8701. Min Range: -1.8701

Max Act: 1.4450. Min Act: -0.0001

Data Index: 190300 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 1.8701. Min Range: -1.8701

Max Act: 1.3936. Min Act: -0.0001

Data Index: 834565 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 1.8701. Min Range: -1.8701

Max Act: 1.4129. Min Act: -0.0001

Data Index: 792562 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 1.8701. Min Range: -1.8701

Max Act: 1.5235. Min Act: -0.0001

Data Index: 510108 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 1.8701. Min Range: -1.8701

Max Act: 1.4135. Min Act: -0.0001

Data Index: 1290418 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 1.8701. Min Range: -1.8701

Max Act: 1.3787. Min Act: -0.0001

Data Index: 547315 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 1.8701. Min Range: -1.8701

Max Act: 1.4364. Min Act: -0.0001

Data Index: 1106908 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 1.8701. Min Range: -1.8701

Max Act: 1.3970. Min Act: -0.0001

Data Index: 890870 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 1.8701. Min Range: -1.8701

Max Act: 1.4014. Min Act: -0.0001

Data Index: 1291146 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 1.8701. Min Range: -1.8701

Max Act: 1.4773. Min Act: -0.0001

Data Index: 1332095 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 1.8701. Min Range: -1.8701

Max Act: 1.4281. Min Act: -0.0001

Data Index: 632806 (C4 (Web Text))

Max Activating Token Index: 370