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

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

Neuron 990 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.7327. Min Act: -0.0000

Data Index: 226451 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.7206. Min Act: -0.0000

Data Index: 105172 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.6602. Min Act: -0.0000

Data Index: 387391 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.6653. Min Act: -0.0000

Data Index: 194544 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1347201 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5558. Min Act: -0.0000

Data Index: 269530 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1303495 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5816. Min Act: -0.0000

Data Index: 908441 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5990. Min Act: -0.0000

Data Index: 474769 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5943. Min Act: -0.0000

Data Index: 202950 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5591. Min Act: -0.0000

Data Index: 970237 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5777. Min Act: -0.0000

Data Index: 143961 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5557. Min Act: -0.0000

Data Index: 430360 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1049744 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5602. Min Act: -0.0000

Data Index: 287728 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5501. Min Act: -0.0000

Data Index: 659892 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5506. Min Act: -0.0000

Data Index: 53902 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5522. Min Act: -0.0000

Data Index: 593189 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5233. Min Act: 0.0000

Data Index: 595714 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5393. Min Act: -0.0000

Data Index: 958301 (C4 (Web Text))

Max Activating Token Index: 438