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

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

Neuron 519 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.7552. Min Act: -0.0000

Data Index: 541785 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.7294. Min Act: -0.0000

Data Index: 807023 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.6038. Min Act: 0.0000

Data Index: 203153 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.5680. Min Act: 0.0000

Data Index: 1208671 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.4165. Min Act: -0.0000

Data Index: 197550 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.3834. Min Act: -0.0000

Data Index: 833325 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.2859. Min Act: -0.0000

Data Index: 407559 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.2730. Min Act: -0.0000

Data Index: 77630 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.2560. Min Act: -0.0000

Data Index: 292297 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.1844. Min Act: -0.0000

Data Index: 870608 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.2473. Min Act: -0.0000

Data Index: 287151 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.2511. Min Act: -0.0000

Data Index: 557299 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.2299. Min Act: -0.0000

Data Index: 376709 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.2112. Min Act: -0.0000

Data Index: 389169 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.2080. Min Act: -0.0000

Data Index: 51257 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.2810. Min Act: -0.0000

Data Index: 556444 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.2683. Min Act: -0.0000

Data Index: 822671 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.1299. Min Act: -0.0000

Data Index: 801882 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.2627. Min Act: -0.0000

Data Index: 951146 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 1.7552. Min Range: -1.7552

Max Act: 1.2501. Min Act: -0.0000

Data Index: 764389 (C4 (Web Text))

Max Activating Token Index: 560