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

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

Neuron 1283 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: 1.1305. Min Range: -1.1305

Max Act: 1.1305. Min Act: -0.0001

Data Index: 706778 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 1.1305. Min Range: -1.1305

Max Act: 1.0336. Min Act: -0.0001

Data Index: 1251902 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.9612. Min Act: -0.0001

Data Index: 956752 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.9738. Min Act: -0.0001

Data Index: 895558 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.8559. Min Act: -0.0001

Data Index: 242397 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.8537. Min Act: -0.0001

Data Index: 805742 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.8787. Min Act: -0.0001

Data Index: 374851 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.8683. Min Act: -0.0001

Data Index: 48404 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.8261. Min Act: -0.0001

Data Index: 1335835 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.8087. Min Act: -0.0001

Data Index: 55547 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.7266. Min Act: -0.0001

Data Index: 627124 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.8417. Min Act: -0.0001

Data Index: 1281986 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.8307. Min Act: -0.0001

Data Index: 172918 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.7512. Min Act: -0.0001

Data Index: 371807 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.7718. Min Act: -0.0001

Data Index: 606877 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.7796. Min Act: -0.0000

Data Index: 643396 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.7588. Min Act: -0.0001

Data Index: 352839 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.7320. Min Act: -0.0001

Data Index: 1006125 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.7429. Min Act: -0.0000

Data Index: 788364 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.7411. Min Act: -0.0001

Data Index: 100853 (C4 (Web Text))

Max Activating Token Index: 658