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

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

Neuron 1222 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0904. Min Range: -1.0904

Max Act: 1.0904. Min Act: -0.0000

Data Index: 573997 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.5906. Min Act: -0.0000

Data Index: 174705 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1307180 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.4867. Min Act: -0.0000

Data Index: 324070 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.5052. Min Act: -0.0000

Data Index: 868850 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.4842. Min Act: -0.0000

Data Index: 1316567 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.5030. Min Act: -0.0000

Data Index: 525842 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.5039. Min Act: -0.0000

Data Index: 54669 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.4634. Min Act: -0.0000

Data Index: 1186197 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1336000 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.4229. Min Act: -0.0000

Data Index: 21562 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.4107. Min Act: -0.0000

Data Index: 1162597 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.4364. Min Act: -0.0000

Data Index: 16799 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.4094. Min Act: -0.0000

Data Index: 335103 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.4092. Min Act: -0.0000

Data Index: 269466 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.3821. Min Act: -0.0000

Data Index: 541781 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1000719 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.4061. Min Act: -0.0000

Data Index: 284545 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1059928 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.4156. Min Act: -0.0000

Data Index: 306743 (C4 (Web Text))

Max Activating Token Index: 772