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

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

Neuron 2463 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0704. Min Range: -1.0704

Max Act: 1.0704. Min Act: -0.0000

Data Index: 467162 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.9596. Min Act: -0.0000

Data Index: 859842 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.9553. Min Act: -0.0000

Data Index: 1348811 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.9445. Min Act: -0.0000

Data Index: 724503 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8996. Min Act: -0.0000

Data Index: 584197 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1012598 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8272. Min Act: -0.0000

Data Index: 567318 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8566. Min Act: -0.0000

Data Index: 807246 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8081. Min Act: -0.0000

Data Index: 783658 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8287. Min Act: -0.0000

Data Index: 660631 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8190. Min Act: -0.0000

Data Index: 84820 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8116. Min Act: -0.0000

Data Index: 184620 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8356. Min Act: -0.0000

Data Index: 85839 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.7721. Min Act: -0.0000

Data Index: 1196217 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.7689. Min Act: -0.0000

Data Index: 243328 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.7936. Min Act: -0.0000

Data Index: 145283 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8199. Min Act: -0.0000

Data Index: 778250 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.7874. Min Act: -0.0000

Data Index: 9569 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.7102. Min Act: -0.0000

Data Index: 707166 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 1.0704. Min Range: -1.0704

Max Act: 0.8342. Min Act: -0.0000

Data Index: 398024 (C4 (Web Text))

Max Activating Token Index: 423