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

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

Neuron 227 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2140. Min Range: -2.2140

Max Act: 2.2140. Min Act: -0.0000

Data Index: 951802 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 2.2140. Min Range: -2.2140

Max Act: 2.2133. Min Act: -0.0000

Data Index: 793969 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 2.2140. Min Range: -2.2140

Max Act: 2.1309. Min Act: -0.0000

Data Index: 595433 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 2.2140. Min Range: -2.2140

Max Act: 1.8451. Min Act: -0.0000

Data Index: 462458 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 2.2140. Min Range: -2.2140

Max Act: 1.9391. Min Act: -0.0000

Data Index: 153009 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 2.2140. Min Range: -2.2140

Max Act: 1.8060. Min Act: -0.0000

Data Index: 184972 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 2.2140. Min Range: -2.2140

Max Act: 1.6874. Min Act: -0.0000

Data Index: 905873 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 2.2140. Min Range: -2.2140

Max Act: 1.8838. Min Act: -0.0000

Data Index: 860774 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 2.2140. Min Range: -2.2140

Max Act: 1.6381. Min Act: -0.0000

Data Index: 293770 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 2.2140. Min Range: -2.2140

Max Act: 1.6980. Min Act: -0.0000

Data Index: 776914 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 2.2140. Min Range: -2.2140

Max Act: 1.6992. Min Act: -0.0000

Data Index: 147539 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 2.2140. Min Range: -2.2140

Max Act: 1.7772. Min Act: -0.0000

Data Index: 608157 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 2.2140. Min Range: -2.2140

Max Act: 1.6071. Min Act: -0.0000

Data Index: 182444 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 2.2140. Min Range: -2.2140

Max Act: 1.6845. Min Act: -0.0000

Data Index: 751087 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 2.2140. Min Range: -2.2140

Max Act: 1.5984. Min Act: -0.0000

Data Index: 698245 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 2.2140. Min Range: -2.2140

Max Act: 1.5622. Min Act: -0.0000

Data Index: 327495 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 2.2140. Min Range: -2.2140

Max Act: 1.4911. Min Act: -0.0000

Data Index: 1022511 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 2.2140. Min Range: -2.2140

Max Act: 1.6355. Min Act: -0.0000

Data Index: 989551 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 2.2140. Min Range: -2.2140

Max Act: 1.5251. Min Act: -0.0000

Data Index: 993036 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 2.2140. Min Range: -2.2140

Max Act: 1.4994. Min Act: -0.0000

Data Index: 250709 (C4 (Web Text))

Max Activating Token Index: 800