Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3705 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.4653. Min Act: -0.0001

Data Index: 715928 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.3456. Min Act: -0.0001

Data Index: 483325 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.3457. Min Act: -0.0001

Data Index: 330548 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.3133. Min Act: -0.0001

Data Index: 731052 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.2979. Min Act: -0.0001

Data Index: 1303298 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.2674. Min Act: -0.0001

Data Index: 1358837 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.2974. Min Act: -0.0001

Data Index: 887965 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.2635. Min Act: -0.0001

Data Index: 818769 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.2355. Min Act: -0.0001

Data Index: 1269721 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.2778. Min Act: -0.0001

Data Index: 953025 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.2660. Min Act: -0.0001

Data Index: 607556 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.2617. Min Act: -0.0001

Data Index: 823788 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.2662. Min Act: -0.0001

Data Index: 652649 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.2569. Min Act: -0.0001

Data Index: 1089037 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.2558. Min Act: -0.0001

Data Index: 248300 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.2623. Min Act: -0.0001

Data Index: 83317 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.2260. Min Act: -0.0001

Data Index: 50168 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.2359. Min Act: -0.0001

Data Index: 145560 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.2317. Min Act: -0.0001

Data Index: 93212 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.4653. Min Range: -0.4653

Max Act: 0.2559. Min Act: -0.0001

Data Index: 755339 (C4 (Web Text))

Max Activating Token Index: 375