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

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

Neuron 4082 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.4788. Min Act: -0.0000

Data Index: 1199837 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 3.4788. Min Range: -3.4788

Max Act: 3.0698. Min Act: -0.0000

Data Index: 1065999 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 3.4788. Min Range: -3.4788

Max Act: 2.8956. Min Act: -0.0000

Data Index: 1150100 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 3.4788. Min Range: -3.4788

Max Act: 2.8120. Min Act: -0.0000

Data Index: 126896 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 3.4788. Min Range: -3.4788

Max Act: 2.7959. Min Act: -0.0000

Data Index: 1030980 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 3.4788. Min Range: -3.4788

Max Act: 2.5952. Min Act: -0.0000

Data Index: 694872 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 3.4788. Min Range: -3.4788

Max Act: 2.8296. Min Act: -0.0000

Data Index: 1099994 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 3.4788. Min Range: -3.4788

Max Act: 2.5275. Min Act: -0.0000

Data Index: 1344127 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 3.4788. Min Range: -3.4788

Max Act: 2.6427. Min Act: -0.0000

Data Index: 120319 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 3.4788. Min Range: -3.4788

Max Act: 2.4396. Min Act: -0.0000

Data Index: 357253 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 3.4788. Min Range: -3.4788

Max Act: 2.3753. Min Act: -0.0000

Data Index: 177580 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 3.4788. Min Range: -3.4788

Max Act: 2.4577. Min Act: -0.0000

Data Index: 789528 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 3.4788. Min Range: -3.4788

Max Act: 2.4499. Min Act: -0.0000

Data Index: 1235970 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 3.4788. Min Range: -3.4788

Max Act: 2.3097. Min Act: -0.0000

Data Index: 567411 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 3.4788. Min Range: -3.4788

Max Act: 2.4497. Min Act: -0.0000

Data Index: 768370 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 3.4788. Min Range: -3.4788

Max Act: 2.3793. Min Act: -0.0000

Data Index: 947397 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 3.4788. Min Range: -3.4788

Max Act: 2.4018. Min Act: -0.0000

Data Index: 1256261 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 3.4788. Min Range: -3.4788

Max Act: 2.5258. Min Act: -0.0000

Data Index: 471590 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 3.4788. Min Range: -3.4788

Max Act: 2.3842. Min Act: -0.0000

Data Index: 999840 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 3.4788. Min Range: -3.4788

Max Act: 2.3764. Min Act: -0.0000

Data Index: 1215357 (C4 (Web Text))

Max Activating Token Index: 145