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

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

Neuron 775 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: 3.8162. Min Range: -3.8162

Max Act: 3.8162. Min Act: -0.0001

Data Index: 483336 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.2468. Min Act: -0.0000

Data Index: 692117 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.1969. Min Act: -0.0000

Data Index: 200288 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.1554. Min Act: -0.0001

Data Index: 902781 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 3.8162. Min Range: -3.8162

Max Act: 2.7883. Min Act: -0.0001

Data Index: 918853 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 3.8162. Min Range: -3.8162

Max Act: 2.9009. Min Act: -0.0001

Data Index: 1050493 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 3.8162. Min Range: -3.8162

Max Act: 2.7393. Min Act: -0.0000

Data Index: 81912 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 3.8162. Min Range: -3.8162

Max Act: 2.5739. Min Act: -0.0001

Data Index: 152297 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 3.8162. Min Range: -3.8162

Max Act: 2.4328. Min Act: -0.0001

Data Index: 1346467 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 3.8162. Min Range: -3.8162

Max Act: 2.5478. Min Act: -0.0001

Data Index: 135040 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 3.8162. Min Range: -3.8162

Max Act: 2.6334. Min Act: -0.0000

Data Index: 327890 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 3.8162. Min Range: -3.8162

Max Act: 2.6335. Min Act: -0.0001

Data Index: 443982 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 3.8162. Min Range: -3.8162

Max Act: 2.4742. Min Act: -0.0000

Data Index: 333410 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 3.8162. Min Range: -3.8162

Max Act: 2.2830. Min Act: -0.0000

Data Index: 428223 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 3.8162. Min Range: -3.8162

Max Act: 2.2651. Min Act: -0.0001

Data Index: 574872 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 3.8162. Min Range: -3.8162

Max Act: 2.3841. Min Act: -0.0001

Data Index: 259609 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 3.8162. Min Range: -3.8162

Max Act: 2.6103. Min Act: -0.0001

Data Index: 18938 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 3.8162. Min Range: -3.8162

Max Act: 2.3539. Min Act: -0.0001

Data Index: 1006992 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 3.8162. Min Range: -3.8162

Max Act: 2.3432. Min Act: -0.0000

Data Index: 1202278 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 3.8162. Min Range: -3.8162

Max Act: 2.5787. Min Act: -0.0001

Data Index: 1145149 (C4 (Web Text))

Max Activating Token Index: 640