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

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

Neuron 2952 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7435. Min Range: -2.7435

Max Act: 2.5597. Min Act: -0.0000

Data Index: 976580 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 2.7435. Min Range: -2.7435

Max Act: 2.7435. Min Act: -0.0000

Data Index: 466582 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 2.7435. Min Range: -2.7435

Max Act: 2.3836. Min Act: -0.0000

Data Index: 1169375 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 2.7435. Min Range: -2.7435

Max Act: 2.6295. Min Act: -0.0000

Data Index: 263768 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 2.7435. Min Range: -2.7435

Max Act: 2.3787. Min Act: -0.0000

Data Index: 1123899 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 2.7435. Min Range: -2.7435

Max Act: 2.3996. Min Act: -0.0000

Data Index: 871732 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 2.7435. Min Range: -2.7435

Max Act: 2.3153. Min Act: -0.0000

Data Index: 1006694 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 2.7435. Min Range: -2.7435

Max Act: 2.0245. Min Act: -0.0000

Data Index: 776564 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 2.7435. Min Range: -2.7435

Max Act: 2.2024. Min Act: -0.0000

Data Index: 932606 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 2.7435. Min Range: -2.7435

Max Act: 2.1933. Min Act: -0.0000

Data Index: 878422 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 2.7435. Min Range: -2.7435

Max Act: 2.3239. Min Act: -0.0000

Data Index: 355897 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 2.7435. Min Range: -2.7435

Max Act: 1.9284. Min Act: -0.0000

Data Index: 1219781 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 2.7435. Min Range: -2.7435

Max Act: 2.1538. Min Act: -0.0000

Data Index: 689716 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 2.7435. Min Range: -2.7435

Max Act: 2.1291. Min Act: -0.0000

Data Index: 802248 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 2.7435. Min Range: -2.7435

Max Act: 2.0998. Min Act: -0.0000

Data Index: 1016409 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 2.7435. Min Range: -2.7435

Max Act: 2.0876. Min Act: -0.0000

Data Index: 333834 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 2.7435. Min Range: -2.7435

Max Act: 1.9521. Min Act: -0.0000

Data Index: 36874 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 2.7435. Min Range: -2.7435

Max Act: 2.1766. Min Act: -0.0000

Data Index: 58497 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 2.7435. Min Range: -2.7435

Max Act: 2.3702. Min Act: -0.0000

Data Index: 210223 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 2.7435. Min Range: -2.7435

Max Act: 2.1345. Min Act: -0.0000

Data Index: 215295 (C4 (Web Text))

Max Activating Token Index: 965