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

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

Neuron 4074 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: 0.4978. Min Range: -0.4978

Max Act: 0.4978. Min Act: -0.0001

Data Index: 681955 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4727. Min Act: -0.0001

Data Index: 415156 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3931. Min Act: -0.0001

Data Index: 1160023 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3979. Min Act: -0.0001

Data Index: 822854 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3987. Min Act: -0.0001

Data Index: 678439 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3563. Min Act: -0.0001

Data Index: 577250 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3806. Min Act: -0.0001

Data Index: 352748 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3261. Min Act: -0.0001

Data Index: 935207 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3661. Min Act: -0.0001

Data Index: 1348336 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3741. Min Act: -0.0001

Data Index: 1094075 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3707. Min Act: -0.0001

Data Index: 1219348 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3359. Min Act: -0.0001

Data Index: 871125 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3451. Min Act: -0.0001

Data Index: 1318694 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3306. Min Act: -0.0001

Data Index: 279064 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3536. Min Act: -0.0001

Data Index: 886740 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3398. Min Act: -0.0001

Data Index: 1187129 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3331. Min Act: -0.0001

Data Index: 559402 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3445. Min Act: -0.0001

Data Index: 440630 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4003. Min Act: -0.0001

Data Index: 249372 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3403. Min Act: -0.0001

Data Index: 490748 (C4 (Web Text))

Max Activating Token Index: 656