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

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

Neuron 1355 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.9753. Min Act: -0.0001

Data Index: 1157787 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.9736. Min Act: -0.0001

Data Index: 121411 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.9259. Min Act: -0.0001

Data Index: 560044 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8788. Min Act: -0.0001

Data Index: 195220 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.9568. Min Act: -0.0001

Data Index: 415520 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.9324. Min Act: -0.0001

Data Index: 82831 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.9206. Min Act: -0.0001

Data Index: 157279 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.9589. Min Act: -0.0001

Data Index: 483138 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.9002. Min Act: -0.0001

Data Index: 274637 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8684. Min Act: -0.0001

Data Index: 594382 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.9104. Min Act: -0.0001

Data Index: 251339 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8715. Min Act: -0.0001

Data Index: 444787 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8839. Min Act: -0.0001

Data Index: 1257517 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8979. Min Act: -0.0001

Data Index: 778231 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8572. Min Act: -0.0001

Data Index: 1293046 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8189. Min Act: -0.0001

Data Index: 75763 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.7815. Min Act: -0.0001

Data Index: 239543 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.7520. Min Act: -0.0001

Data Index: 954470 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.7279. Min Act: -0.0001

Data Index: 24923 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8001. Min Act: -0.0001

Data Index: 569862 (C4 (Web Text))

Max Activating Token Index: 370