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

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

Neuron 665 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1601. Min Range: -1.1601

Max Act: 1.1601. Min Act: -0.0001

Data Index: 140597 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 1.1601. Min Range: -1.1601

Max Act: 1.1354. Min Act: -0.0001

Data Index: 1239969 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 1.1601. Min Range: -1.1601

Max Act: 1.1553. Min Act: -0.0001

Data Index: 469191 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 1.1601. Min Range: -1.1601

Max Act: 1.0271. Min Act: -0.0001

Data Index: 297777 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.9532. Min Act: -0.0001

Data Index: 753851 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.9451. Min Act: -0.0001

Data Index: 67716 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.9403. Min Act: -0.0001

Data Index: 1064794 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.9632. Min Act: -0.0001

Data Index: 1234186 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.9265. Min Act: -0.0001

Data Index: 871009 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.9324. Min Act: -0.0001

Data Index: 77636 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.9069. Min Act: -0.0001

Data Index: 685624 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.8478. Min Act: -0.0001

Data Index: 1131964 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.8964. Min Act: -0.0001

Data Index: 964100 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.8759. Min Act: -0.0001

Data Index: 59314 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.9011. Min Act: -0.0001

Data Index: 1186912 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.8269. Min Act: -0.0001

Data Index: 331256 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.8763. Min Act: -0.0001

Data Index: 962476 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.8618. Min Act: -0.0001

Data Index: 895523 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.8279. Min Act: -0.0001

Data Index: 149652 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 1.1601. Min Range: -1.1601

Max Act: 0.8246. Min Act: -0.0001

Data Index: 1198940 (C4 (Web Text))

Max Activating Token Index: 921