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

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

Neuron 892 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: 1.4103. Min Range: -1.4103

Max Act: 1.4103. Min Act: -0.0000

Data Index: 78723 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 1.4103. Min Range: -1.4103

Max Act: 1.1384. Min Act: -0.0000

Data Index: 231772 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 1.4103. Min Range: -1.4103

Max Act: 0.8648. Min Act: -0.0000

Data Index: 255002 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 1.4103. Min Range: -1.4103

Max Act: 1.0171. Min Act: -0.0000

Data Index: 447462 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 1.4103. Min Range: -1.4103

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1623558 (Python Code)

Max Activating Token Index: 319

Text #5

Max Range: 1.4103. Min Range: -1.4103

Max Act: 0.8778. Min Act: -0.0000

Data Index: 171887 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 1.4103. Min Range: -1.4103

Max Act: 0.8415. Min Act: -0.0000

Data Index: 232431 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 1.4103. Min Range: -1.4103

Max Act: 0.7752. Min Act: -0.0000

Data Index: 185668 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 1.4103. Min Range: -1.4103

Max Act: 0.7961. Min Act: -0.0000

Data Index: 855874 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 1.4103. Min Range: -1.4103

Max Act: 0.7775. Min Act: -0.0000

Data Index: 5080 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 1.4103. Min Range: -1.4103

Max Act: 0.8502. Min Act: -0.0000

Data Index: 486697 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 1.4103. Min Range: -1.4103

Max Act: 0.7902. Min Act: -0.0000

Data Index: 1030041 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 1.4103. Min Range: -1.4103

Max Act: 0.8211. Min Act: -0.0000

Data Index: 110962 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 1.4103. Min Range: -1.4103

Max Act: 0.7126. Min Act: -0.0000

Data Index: 954847 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 1.4103. Min Range: -1.4103

Max Act: 0.7148. Min Act: -0.0000

Data Index: 48741 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 1.4103. Min Range: -1.4103

Max Act: 0.6945. Min Act: -0.0000

Data Index: 1098733 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 1.4103. Min Range: -1.4103

Max Act: 0.7778. Min Act: -0.0000

Data Index: 310677 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 1.4103. Min Range: -1.4103

Max Act: 0.7024. Min Act: -0.0000

Data Index: 991104 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 1.4103. Min Range: -1.4103

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1310883 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 1.4103. Min Range: -1.4103

Max Act: 0.6538. Min Act: -0.0000

Data Index: 526933 (C4 (Web Text))

Max Activating Token Index: 803