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

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

Neuron 3665 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0878. Min Range: -1.0878

Max Act: 1.0878. Min Act: -0.0001

Data Index: 660365 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 1.0878. Min Range: -1.0878

Max Act: 1.0030. Min Act: -0.0001

Data Index: 1301471 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 1.0878. Min Range: -1.0878

Max Act: 0.9098. Min Act: -0.0001

Data Index: 288757 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 1.0878. Min Range: -1.0878

Max Act: 0.9296. Min Act: -0.0001

Data Index: 555233 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 1.0878. Min Range: -1.0878

Max Act: 0.7993. Min Act: -0.0001

Data Index: 1173352 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 1.0878. Min Range: -1.0878

Max Act: 0.9182. Min Act: -0.0001

Data Index: 433988 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 1.0878. Min Range: -1.0878

Max Act: 0.8327. Min Act: -0.0001

Data Index: 274398 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 1.0878. Min Range: -1.0878

Max Act: 0.8560. Min Act: -0.0001

Data Index: 873001 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 1.0878. Min Range: -1.0878

Max Act: 0.8476. Min Act: -0.0001

Data Index: 246558 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 1.0878. Min Range: -1.0878

Max Act: 0.8291. Min Act: -0.0001

Data Index: 921006 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 1.0878. Min Range: -1.0878

Max Act: 0.8875. Min Act: -0.0001

Data Index: 734801 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 1.0878. Min Range: -1.0878

Max Act: 0.8790. Min Act: -0.0001

Data Index: 622534 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 1.0878. Min Range: -1.0878

Max Act: 0.8537. Min Act: -0.0001

Data Index: 937076 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 1.0878. Min Range: -1.0878

Max Act: 0.8126. Min Act: -0.0001

Data Index: 761748 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 1.0878. Min Range: -1.0878

Max Act: 0.7775. Min Act: -0.0001

Data Index: 408220 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 1.0878. Min Range: -1.0878

Max Act: 0.7638. Min Act: -0.0001

Data Index: 397711 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 1.0878. Min Range: -1.0878

Max Act: 0.8086. Min Act: -0.0001

Data Index: 278221 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 1.0878. Min Range: -1.0878

Max Act: 0.7927. Min Act: -0.0001

Data Index: 1290251 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 1.0878. Min Range: -1.0878

Max Act: 0.7517. Min Act: -0.0001

Data Index: 1292708 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 1.0878. Min Range: -1.0878

Max Act: 0.7594. Min Act: -0.0001

Data Index: 1044084 (C4 (Web Text))

Max Activating Token Index: 994