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

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

Neuron 2131 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.8389. Min Act: -0.0001

Data Index: 1415462 (Python Code)

Max Activating Token Index: 724

Text #1

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.7944. Min Act: -0.0001

Data Index: 271896 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.7419. Min Act: -0.0001

Data Index: 1278856 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.7162. Min Act: -0.0001

Data Index: 61384 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.7366. Min Act: -0.0001

Data Index: 1624765 (Python Code)

Max Activating Token Index: 792

Text #5

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.6689. Min Act: -0.0001

Data Index: 637577 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.7206. Min Act: -0.0001

Data Index: 1269193 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.7470. Min Act: -0.0001

Data Index: 1029179 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.7194. Min Act: -0.0001

Data Index: 551761 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.6684. Min Act: -0.0001

Data Index: 405066 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5856. Min Act: -0.0001

Data Index: 1354293 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.6651. Min Act: -0.0001

Data Index: 29157 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.6725. Min Act: -0.0001

Data Index: 253617 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.6270. Min Act: -0.0001

Data Index: 371945 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.6861. Min Act: -0.0001

Data Index: 1310006 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.6808. Min Act: -0.0001

Data Index: 798480 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.6600. Min Act: -0.0001

Data Index: 879156 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.6806. Min Act: -0.0001

Data Index: 526029 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.6590. Min Act: -0.0001

Data Index: 461763 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.6480. Min Act: -0.0001

Data Index: 1623422 (Python Code)

Max Activating Token Index: 58