Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2700 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3343. Min Range: -2.3343

Max Act: 2.3343. Min Act: -0.0000

Data Index: 970127 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 2.3343. Min Range: -2.3343

Max Act: 1.9676. Min Act: -0.0000

Data Index: 172989 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 2.3343. Min Range: -2.3343

Max Act: 1.9417. Min Act: -0.0000

Data Index: 685338 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 2.3343. Min Range: -2.3343

Max Act: 1.6643. Min Act: -0.0001

Data Index: 1306566 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 2.3343. Min Range: -2.3343

Max Act: 1.5883. Min Act: -0.0001

Data Index: 944617 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 2.3343. Min Range: -2.3343

Max Act: 1.4149. Min Act: -0.0000

Data Index: 22579 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 2.3343. Min Range: -2.3343

Max Act: 1.3699. Min Act: -0.0001

Data Index: 70247 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 2.3343. Min Range: -2.3343

Max Act: 1.2841. Min Act: -0.0000

Data Index: 1313034 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 2.3343. Min Range: -2.3343

Max Act: 1.3726. Min Act: -0.0001

Data Index: 1259680 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 2.3343. Min Range: -2.3343

Max Act: 1.3388. Min Act: -0.0001

Data Index: 543678 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 2.3343. Min Range: -2.3343

Max Act: 1.3119. Min Act: -0.0000

Data Index: 1445540 (Python Code)

Max Activating Token Index: 254

Text #11

Max Range: 2.3343. Min Range: -2.3343

Max Act: 1.3372. Min Act: -0.0000

Data Index: 1336085 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 2.3343. Min Range: -2.3343

Max Act: 1.4054. Min Act: -0.0000

Data Index: 1098997 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 2.3343. Min Range: -2.3343

Max Act: 1.3770. Min Act: -0.0000

Data Index: 167562 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 2.3343. Min Range: -2.3343

Max Act: 1.3419. Min Act: -0.0000

Data Index: 860650 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 2.3343. Min Range: -2.3343

Max Act: 1.3651. Min Act: -0.0001

Data Index: 1302438 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 2.3343. Min Range: -2.3343

Max Act: 1.2485. Min Act: -0.0000

Data Index: 191258 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 2.3343. Min Range: -2.3343

Max Act: 1.3458. Min Act: -0.0000

Data Index: 850535 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 2.3343. Min Range: -2.3343

Max Act: 1.2539. Min Act: -0.0000

Data Index: 603209 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 2.3343. Min Range: -2.3343

Max Act: 1.2678. Min Act: -0.0000

Data Index: 760245 (C4 (Web Text))

Max Activating Token Index: 625