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

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

Neuron 2040 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1759. Min Range: -1.1759

Max Act: 1.1759. Min Act: -0.0001

Data Index: 1356857 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 1.1759. Min Range: -1.1759

Max Act: 1.0042. Min Act: -0.0001

Data Index: 190024 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 1.1759. Min Range: -1.1759

Max Act: 1.0307. Min Act: -0.0000

Data Index: 579138 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 1.1759. Min Range: -1.1759

Max Act: 1.0349. Min Act: -0.0000

Data Index: 957661 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 1.1759. Min Range: -1.1759

Max Act: 1.0275. Min Act: -0.0000

Data Index: 1321713 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.9505. Min Act: -0.0000

Data Index: 497851 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.9490. Min Act: -0.0000

Data Index: 29560 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.8896. Min Act: -0.0001

Data Index: 1180819 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.9199. Min Act: -0.0000

Data Index: 1080287 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.9679. Min Act: -0.0001

Data Index: 82880 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.9324. Min Act: -0.0000

Data Index: 704756 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.9313. Min Act: -0.0000

Data Index: 349294 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.8810. Min Act: -0.0000

Data Index: 624965 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.8763. Min Act: -0.0000

Data Index: 662103 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.8772. Min Act: -0.0000

Data Index: 814097 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.9361. Min Act: -0.0000

Data Index: 141932 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.8715. Min Act: -0.0000

Data Index: 246244 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.8762. Min Act: -0.0001

Data Index: 1026707 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.9300. Min Act: -0.0000

Data Index: 803943 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 1.1759. Min Range: -1.1759

Max Act: 0.9008. Min Act: -0.0001

Data Index: 743586 (C4 (Web Text))

Max Activating Token Index: 497