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

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

Neuron 255 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.5744. Min Act: -0.0000

Data Index: 866363 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.5757. Min Act: -0.0000

Data Index: 798047 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.5214. Min Act: -0.0000

Data Index: 296838 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1215453 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4670. Min Act: -0.0000

Data Index: 406678 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1170997 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4168. Min Act: -0.0000

Data Index: 658960 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1309783 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1339444 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1318683 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4038. Min Act: -0.0000

Data Index: 164773 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.3857. Min Act: -0.0000

Data Index: 78058 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.3891. Min Act: -0.0000

Data Index: 1146250 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4076. Min Act: -0.0000

Data Index: 753690 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.3922. Min Act: -0.0000

Data Index: 399393 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.3923. Min Act: -0.0000

Data Index: 520650 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.3796. Min Act: -0.0000

Data Index: 815313 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.4037. Min Act: -0.0000

Data Index: 16556 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.3665. Min Act: -0.0000

Data Index: 91495 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 0.5757. Min Range: -0.5757

Max Act: 0.3605. Min Act: -0.0000

Data Index: 371931 (C4 (Web Text))

Max Activating Token Index: 875