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

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

Neuron 2432 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: 2.0910. Min Range: -2.0910

Max Act: 2.0910. Min Act: -0.0000

Data Index: 1249731 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 2.0910. Min Range: -2.0910

Max Act: 1.9802. Min Act: -0.0000

Data Index: 564644 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 2.0910. Min Range: -2.0910

Max Act: 1.9057. Min Act: -0.0000

Data Index: 449236 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 2.0910. Min Range: -2.0910

Max Act: 1.7871. Min Act: -0.0000

Data Index: 1308053 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 2.0910. Min Range: -2.0910

Max Act: 1.9186. Min Act: -0.0000

Data Index: 1096425 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 2.0910. Min Range: -2.0910

Max Act: 1.6148. Min Act: -0.0000

Data Index: 280665 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 2.0910. Min Range: -2.0910

Max Act: 1.7063. Min Act: -0.0000

Data Index: 506018 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 2.0910. Min Range: -2.0910

Max Act: 1.3836. Min Act: -0.0000

Data Index: 217945 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 2.0910. Min Range: -2.0910

Max Act: 1.3699. Min Act: -0.0000

Data Index: 682739 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 2.0910. Min Range: -2.0910

Max Act: 1.3288. Min Act: -0.0000

Data Index: 1261932 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 2.0910. Min Range: -2.0910

Max Act: 1.2618. Min Act: -0.0000

Data Index: 1180303 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 2.0910. Min Range: -2.0910

Max Act: 1.2287. Min Act: -0.0000

Data Index: 275405 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 2.0910. Min Range: -2.0910

Max Act: 1.0935. Min Act: -0.0000

Data Index: 1047908 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 2.0910. Min Range: -2.0910

Max Act: 1.2624. Min Act: -0.0000

Data Index: 1034877 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 2.0910. Min Range: -2.0910

Max Act: 1.0710. Min Act: -0.0000

Data Index: 238103 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 2.0910. Min Range: -2.0910

Max Act: 1.0530. Min Act: -0.0000

Data Index: 386605 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 2.0910. Min Range: -2.0910

Max Act: 1.0071. Min Act: -0.0000

Data Index: 1043944 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 2.0910. Min Range: -2.0910

Max Act: 1.1096. Min Act: -0.0000

Data Index: 816036 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 2.0910. Min Range: -2.0910

Max Act: 1.0137. Min Act: -0.0000

Data Index: 1150107 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 2.0910. Min Range: -2.0910

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1495196 (Python Code)

Max Activating Token Index: 966