Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2056 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.5605. Min Act: -0.0000

Data Index: 237879 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 5.5605. Min Range: -5.5605

Max Act: 4.7798. Min Act: -0.0000

Data Index: 441696 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 5.5605. Min Range: -5.5605

Max Act: 4.4740. Min Act: -0.0000

Data Index: 905340 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 5.5605. Min Range: -5.5605

Max Act: 4.1145. Min Act: -0.0000

Data Index: 122271 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 5.5605. Min Range: -5.5605

Max Act: 4.4433. Min Act: -0.0000

Data Index: 640821 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 5.5605. Min Range: -5.5605

Max Act: 4.1552. Min Act: -0.0000

Data Index: 551321 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 5.5605. Min Range: -5.5605

Max Act: 4.3012. Min Act: -0.0000

Data Index: 1114099 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 5.5605. Min Range: -5.5605

Max Act: 3.8335. Min Act: -0.0000

Data Index: 906357 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 5.5605. Min Range: -5.5605

Max Act: 3.8328. Min Act: -0.0000

Data Index: 466810 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 5.5605. Min Range: -5.5605

Max Act: 3.8335. Min Act: -0.0000

Data Index: 902361 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 5.5605. Min Range: -5.5605

Max Act: 3.6309. Min Act: -0.0000

Data Index: 44328 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 5.5605. Min Range: -5.5605

Max Act: 3.9550. Min Act: -0.0000

Data Index: 47064 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 5.5605. Min Range: -5.5605

Max Act: 3.7490. Min Act: -0.0000

Data Index: 152929 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 5.5605. Min Range: -5.5605

Max Act: 3.7279. Min Act: -0.0000

Data Index: 1130310 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 5.5605. Min Range: -5.5605

Max Act: 3.5808. Min Act: -0.0000

Data Index: 280600 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 5.5605. Min Range: -5.5605

Max Act: 3.6693. Min Act: -0.0000

Data Index: 774305 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 5.5605. Min Range: -5.5605

Max Act: 3.5033. Min Act: -0.0000

Data Index: 882605 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 5.5605. Min Range: -5.5605

Max Act: 3.4832. Min Act: -0.0000

Data Index: 1271607 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 5.5605. Min Range: -5.5605

Max Act: 3.5736. Min Act: -0.0000

Data Index: 729514 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 5.5605. Min Range: -5.5605

Max Act: 3.3970. Min Act: -0.0000

Data Index: 1320299 (C4 (Web Text))

Max Activating Token Index: 836