Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1972 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.1166. Min Act: -0.0003

Data Index: 1592800 (Python Code)

Max Activating Token Index: 829

Text #1

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.1113. Min Act: -0.0003

Data Index: 1402600 (Python Code)

Max Activating Token Index: 651

Text #2

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.1114. Min Act: -0.0003

Data Index: 791779 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.1044. Min Act: -0.0003

Data Index: 468078 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0993. Min Act: -0.0003

Data Index: 1629100 (Python Code)

Max Activating Token Index: 478

Text #5

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0964. Min Act: -0.0003

Data Index: 255793 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0935. Min Act: -0.0004

Data Index: 1401699 (Python Code)

Max Activating Token Index: 959

Text #7

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0999. Min Act: -0.0003

Data Index: 1467470 (Python Code)

Max Activating Token Index: 947

Text #8

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0931. Min Act: -0.0003

Data Index: 1590149 (Python Code)

Max Activating Token Index: 421

Text #9

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0924. Min Act: -0.0003

Data Index: 258591 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0960. Min Act: -0.0003

Data Index: 69378 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0915. Min Act: -0.0003

Data Index: 1638849 (Python Code)

Max Activating Token Index: 691

Text #12

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0922. Min Act: -0.0003

Data Index: 270474 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0966. Min Act: -0.0003

Data Index: 452496 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0884. Min Act: -0.0003

Data Index: 1591942 (Python Code)

Max Activating Token Index: 847

Text #15

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0882. Min Act: -0.0003

Data Index: 1587159 (Python Code)

Max Activating Token Index: 992

Text #16

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0896. Min Act: -0.0003

Data Index: 1537714 (Python Code)

Max Activating Token Index: 843

Text #17

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0865. Min Act: -0.0003

Data Index: 1409394 (Python Code)

Max Activating Token Index: 776

Text #18

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0899. Min Act: -0.0003

Data Index: 1406434 (Python Code)

Max Activating Token Index: 953

Text #19

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0895. Min Act: -0.0004

Data Index: 372834 (C4 (Web Text))

Max Activating Token Index: 932