Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2918 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0492. Min Act: -0.0001

Data Index: 989992 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0434. Min Act: -0.0001

Data Index: 649041 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0470. Min Act: -0.0001

Data Index: 1091152 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0446. Min Act: -0.0001

Data Index: 340645 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0403. Min Act: -0.0001

Data Index: 763262 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0432. Min Act: -0.0001

Data Index: 867737 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0453. Min Act: -0.0001

Data Index: 364173 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1265831 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0438. Min Act: -0.0001

Data Index: 384921 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0414. Min Act: -0.0001

Data Index: 1197815 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0414. Min Act: -0.0001

Data Index: 630622 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0421. Min Act: -0.0001

Data Index: 679521 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0450. Min Act: -0.0001

Data Index: 916870 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0419. Min Act: -0.0001

Data Index: 993463 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0412. Min Act: -0.0001

Data Index: 592224 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0421. Min Act: -0.0001

Data Index: 100975 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0401. Min Act: -0.0001

Data Index: 457188 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0383. Min Act: -0.0001

Data Index: 181498 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0404. Min Act: -0.0001

Data Index: 329222 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0387. Min Act: -0.0001

Data Index: 166603 (C4 (Web Text))

Max Activating Token Index: 501