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

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

Neuron 5958 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7801. Min Range: -4.7801

Max Act: 4.7801. Min Act: -0.0000

Data Index: 686624 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 4.7801. Min Range: -4.7801

Max Act: 4.5490. Min Act: -0.0000

Data Index: 485416 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 4.7801. Min Range: -4.7801

Max Act: 4.2025. Min Act: -0.0000

Data Index: 1032618 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 4.7801. Min Range: -4.7801

Max Act: 4.0576. Min Act: -0.0000

Data Index: 514320 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 4.7801. Min Range: -4.7801

Max Act: 3.5738. Min Act: -0.0000

Data Index: 1219635 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 4.7801. Min Range: -4.7801

Max Act: 3.8023. Min Act: -0.0000

Data Index: 133196 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 4.7801. Min Range: -4.7801

Max Act: 3.7577. Min Act: -0.0000

Data Index: 1097683 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 4.7801. Min Range: -4.7801

Max Act: 3.7423. Min Act: -0.0000

Data Index: 839566 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 4.7801. Min Range: -4.7801

Max Act: 3.7989. Min Act: -0.0000

Data Index: 848476 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 4.7801. Min Range: -4.7801

Max Act: 3.4750. Min Act: -0.0000

Data Index: 571007 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 4.7801. Min Range: -4.7801

Max Act: 3.5781. Min Act: -0.0000

Data Index: 1326421 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 4.7801. Min Range: -4.7801

Max Act: 3.7445. Min Act: -0.0000

Data Index: 248790 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 4.7801. Min Range: -4.7801

Max Act: 3.5722. Min Act: -0.0000

Data Index: 330330 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 4.7801. Min Range: -4.7801

Max Act: 3.5533. Min Act: -0.0000

Data Index: 99066 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 4.7801. Min Range: -4.7801

Max Act: 3.5274. Min Act: -0.0000

Data Index: 805953 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 4.7801. Min Range: -4.7801

Max Act: 3.5030. Min Act: -0.0000

Data Index: 138109 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 4.7801. Min Range: -4.7801

Max Act: 3.4992. Min Act: -0.0000

Data Index: 990283 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 4.7801. Min Range: -4.7801

Max Act: 3.5400. Min Act: -0.0000

Data Index: 1304979 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 4.7801. Min Range: -4.7801

Max Act: 3.2964. Min Act: -0.0000

Data Index: 379684 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 4.7801. Min Range: -4.7801

Max Act: 3.2510. Min Act: -0.0000

Data Index: 370535 (C4 (Web Text))

Max Activating Token Index: 953