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

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

Neuron 904 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 14.9544. Min Range: -14.9544

Max Act: 14.9544. Min Act: -0.0000

Data Index: 220562 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 14.9544. Min Range: -14.9544

Max Act: 14.5497. Min Act: -0.0000

Data Index: 630924 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 14.9544. Min Range: -14.9544

Max Act: 13.4733. Min Act: -0.0000

Data Index: 727765 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 14.9544. Min Range: -14.9544

Max Act: 13.6112. Min Act: -0.0000

Data Index: 929223 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 14.9544. Min Range: -14.9544

Max Act: 13.5220. Min Act: -0.0000

Data Index: 511885 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 14.9544. Min Range: -14.9544

Max Act: 13.4250. Min Act: -0.0000

Data Index: 100410 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 14.9544. Min Range: -14.9544

Max Act: 12.8658. Min Act: -0.0000

Data Index: 990202 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 14.9544. Min Range: -14.9544

Max Act: 13.5391. Min Act: -0.0000

Data Index: 900707 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 14.9544. Min Range: -14.9544

Max Act: 13.5166. Min Act: -0.0000

Data Index: 1038543 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 14.9544. Min Range: -14.9544

Max Act: 13.2465. Min Act: -0.0000

Data Index: 257139 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 14.9544. Min Range: -14.9544

Max Act: 13.7254. Min Act: -0.0000

Data Index: 667923 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 14.9544. Min Range: -14.9544

Max Act: 13.0288. Min Act: -0.0000

Data Index: 353400 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 14.9544. Min Range: -14.9544

Max Act: 13.3922. Min Act: -0.0000

Data Index: 367394 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 14.9544. Min Range: -14.9544

Max Act: 12.5450. Min Act: -0.0000

Data Index: 1159467 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 14.9544. Min Range: -14.9544

Max Act: 12.9994. Min Act: -0.0000

Data Index: 356964 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 14.9544. Min Range: -14.9544

Max Act: 12.7363. Min Act: -0.0000

Data Index: 1004092 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 14.9544. Min Range: -14.9544

Max Act: 13.1318. Min Act: -0.0000

Data Index: 1167622 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 14.9544. Min Range: -14.9544

Max Act: 12.8047. Min Act: -0.0000

Data Index: 326732 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 14.9544. Min Range: -14.9544

Max Act: 12.8641. Min Act: -0.0000

Data Index: 226717 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 14.9544. Min Range: -14.9544

Max Act: 12.9366. Min Act: -0.0000

Data Index: 687694 (C4 (Web Text))

Max Activating Token Index: 333