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

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

Neuron 4007 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: 2.7841. Min Range: -2.7841

Max Act: 2.7759. Min Act: -0.0000

Data Index: 751763 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 2.7841. Min Range: -2.7841

Max Act: 2.7841. Min Act: -0.0000

Data Index: 908118 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 2.7841. Min Range: -2.7841

Max Act: 2.7069. Min Act: -0.0000

Data Index: 117969 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 2.7841. Min Range: -2.7841

Max Act: 2.5034. Min Act: -0.0000

Data Index: 506587 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 2.7841. Min Range: -2.7841

Max Act: 2.4911. Min Act: -0.0000

Data Index: 959952 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 2.7841. Min Range: -2.7841

Max Act: 2.5104. Min Act: -0.0000

Data Index: 494804 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 2.7841. Min Range: -2.7841

Max Act: 2.5624. Min Act: -0.0000

Data Index: 482320 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 2.7841. Min Range: -2.7841

Max Act: 1.6519. Min Act: -0.0000

Data Index: 931371 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 2.7841. Min Range: -2.7841

Max Act: 1.5854. Min Act: -0.0000

Data Index: 824472 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 2.7841. Min Range: -2.7841

Max Act: 1.4601. Min Act: -0.0000

Data Index: 20830 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 2.7841. Min Range: -2.7841

Max Act: 1.4434. Min Act: -0.0000

Data Index: 1338156 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 2.7841. Min Range: -2.7841

Max Act: 1.5052. Min Act: -0.0000

Data Index: 614875 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 2.7841. Min Range: -2.7841

Max Act: 1.5020. Min Act: -0.0000

Data Index: 353865 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 2.7841. Min Range: -2.7841

Max Act: 1.4244. Min Act: -0.0000

Data Index: 275226 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 2.7841. Min Range: -2.7841

Max Act: 1.3672. Min Act: -0.0000

Data Index: 1353235 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 2.7841. Min Range: -2.7841

Max Act: 1.2786. Min Act: -0.0000

Data Index: 1143232 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 2.7841. Min Range: -2.7841

Max Act: 1.3465. Min Act: -0.0000

Data Index: 381243 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 2.7841. Min Range: -2.7841

Max Act: 1.3713. Min Act: -0.0000

Data Index: 17204 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 2.7841. Min Range: -2.7841

Max Act: 1.1790. Min Act: -0.0000

Data Index: 886987 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 2.7841. Min Range: -2.7841

Max Act: 1.2057. Min Act: -0.0000

Data Index: 53912 (C4 (Web Text))

Max Activating Token Index: 738