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

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

Neuron 2560 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: 1.4145. Min Range: -1.4145

Max Act: 1.4145. Min Act: -0.0000

Data Index: 477558 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.3436. Min Act: -0.0000

Data Index: 1105000 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.3637. Min Act: -0.0000

Data Index: 1076571 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.2988. Min Act: -0.0000

Data Index: 865880 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.2960. Min Act: -0.0000

Data Index: 369349 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.3006. Min Act: -0.0000

Data Index: 1206920 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.3193. Min Act: -0.0000

Data Index: 101588 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.2691. Min Act: -0.0000

Data Index: 1295920 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.3110. Min Act: -0.0000

Data Index: 932944 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.2711. Min Act: -0.0000

Data Index: 1322158 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.2091. Min Act: -0.0000

Data Index: 973333 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.2202. Min Act: -0.0000

Data Index: 189882 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.2246. Min Act: -0.0000

Data Index: 1100581 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.1971. Min Act: -0.0000

Data Index: 420645 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.1850. Min Act: -0.0000

Data Index: 267276 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.1883. Min Act: -0.0000

Data Index: 413433 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.0722. Min Act: -0.0000

Data Index: 193671 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.2341. Min Act: -0.0000

Data Index: 1116695 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.1549. Min Act: -0.0000

Data Index: 905090 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 1.4145. Min Range: -1.4145

Max Act: 1.1211. Min Act: -0.0000

Data Index: 598875 (C4 (Web Text))

Max Activating Token Index: 885