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

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

Neuron 5080 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0057. Min Range: -5.0057

Max Act: 5.0057. Min Act: -0.0001

Data Index: 1228121 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 5.0057. Min Range: -5.0057

Max Act: 4.7173. Min Act: -0.0001

Data Index: 301765 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 5.0057. Min Range: -5.0057

Max Act: 4.6982. Min Act: -0.0001

Data Index: 679994 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 5.0057. Min Range: -5.0057

Max Act: 4.3708. Min Act: -0.0001

Data Index: 326818 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 5.0057. Min Range: -5.0057

Max Act: 4.8384. Min Act: -0.0001

Data Index: 202666 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 5.0057. Min Range: -5.0057

Max Act: 4.2784. Min Act: -0.0001

Data Index: 902923 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 5.0057. Min Range: -5.0057

Max Act: 4.7613. Min Act: -0.0001

Data Index: 508260 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 5.0057. Min Range: -5.0057

Max Act: 4.0488. Min Act: -0.0001

Data Index: 320312 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 5.0057. Min Range: -5.0057

Max Act: 4.3551. Min Act: -0.0001

Data Index: 1342390 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 5.0057. Min Range: -5.0057

Max Act: 4.4667. Min Act: -0.0001

Data Index: 593529 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 5.0057. Min Range: -5.0057

Max Act: 4.2744. Min Act: -0.0001

Data Index: 1202042 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 5.0057. Min Range: -5.0057

Max Act: 4.2319. Min Act: -0.0001

Data Index: 932019 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 5.0057. Min Range: -5.0057

Max Act: 4.4437. Min Act: -0.0001

Data Index: 1028121 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 5.0057. Min Range: -5.0057

Max Act: 4.4181. Min Act: -0.0001

Data Index: 1095970 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 5.0057. Min Range: -5.0057

Max Act: 4.3732. Min Act: -0.0001

Data Index: 1048727 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 5.0057. Min Range: -5.0057

Max Act: 4.1890. Min Act: -0.0001

Data Index: 767005 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 5.0057. Min Range: -5.0057

Max Act: 4.1448. Min Act: -0.0001

Data Index: 577874 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 5.0057. Min Range: -5.0057

Max Act: 4.3040. Min Act: -0.0001

Data Index: 511473 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 5.0057. Min Range: -5.0057

Max Act: 4.6126. Min Act: -0.0001

Data Index: 1026880 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 5.0057. Min Range: -5.0057

Max Act: 4.5320. Min Act: -0.0001

Data Index: 872054 (C4 (Web Text))

Max Activating Token Index: 715