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

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

Neuron 2077 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.3764. Min Range: -4.3764

Max Act: 4.3764. Min Act: -0.0000

Data Index: 897503 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 4.3764. Min Range: -4.3764

Max Act: 3.5972. Min Act: -0.0000

Data Index: 25796 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 4.3764. Min Range: -4.3764

Max Act: 3.1583. Min Act: -0.0000

Data Index: 688337 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 4.3764. Min Range: -4.3764

Max Act: 2.8463. Min Act: -0.0000

Data Index: 685239 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 4.3764. Min Range: -4.3764

Max Act: 2.5340. Min Act: -0.0000

Data Index: 1039004 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 4.3764. Min Range: -4.3764

Max Act: 2.3849. Min Act: -0.0000

Data Index: 665265 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 4.3764. Min Range: -4.3764

Max Act: 2.2054. Min Act: -0.0000

Data Index: 344706 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 4.3764. Min Range: -4.3764

Max Act: 2.2807. Min Act: -0.0000

Data Index: 1250769 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 4.3764. Min Range: -4.3764

Max Act: 1.9385. Min Act: -0.0000

Data Index: 1586670 (Python Code)

Max Activating Token Index: 994

Text #9

Max Range: 4.3764. Min Range: -4.3764

Max Act: 1.9968. Min Act: -0.0000

Data Index: 925116 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 4.3764. Min Range: -4.3764

Max Act: 1.6690. Min Act: -0.0000

Data Index: 360071 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 4.3764. Min Range: -4.3764

Max Act: 1.4493. Min Act: -0.0000

Data Index: 293023 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 4.3764. Min Range: -4.3764

Max Act: 1.5047. Min Act: -0.0000

Data Index: 147467 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 4.3764. Min Range: -4.3764

Max Act: 1.5227. Min Act: -0.0000

Data Index: 340937 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 4.3764. Min Range: -4.3764

Max Act: 1.4501. Min Act: -0.0000

Data Index: 96114 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 4.3764. Min Range: -4.3764

Max Act: 1.4039. Min Act: -0.0000

Data Index: 383804 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 4.3764. Min Range: -4.3764

Max Act: 1.5303. Min Act: -0.0000

Data Index: 345458 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 4.3764. Min Range: -4.3764

Max Act: 1.4291. Min Act: -0.0000

Data Index: 748691 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 4.3764. Min Range: -4.3764

Max Act: 1.2850. Min Act: -0.0000

Data Index: 303610 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 4.3764. Min Range: -4.3764

Max Act: 1.3979. Min Act: -0.0000

Data Index: 283808 (C4 (Web Text))

Max Activating Token Index: 340