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

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

Neuron 2661 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.3051. Min Act: -0.0000

Data Index: 311718 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.2137. Min Act: -0.0000

Data Index: 1189715 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.2011. Min Act: -0.0000

Data Index: 955635 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.1938. Min Act: -0.0000

Data Index: 168606 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.2050. Min Act: 0.0000

Data Index: 841101 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.1870. Min Act: -0.0000

Data Index: 998690 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.1892. Min Act: -0.0000

Data Index: 215887 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1063857 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.1885. Min Act: -0.0000

Data Index: 60198 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.1738. Min Act: -0.0000

Data Index: 275814 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.1802. Min Act: -0.0000

Data Index: 910742 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.1788. Min Act: -0.0000

Data Index: 699291 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.1689. Min Act: -0.0000

Data Index: 56105 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.1700. Min Act: -0.0000

Data Index: 534654 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.1717. Min Act: -0.0000

Data Index: 552205 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.1714. Min Act: -0.0000

Data Index: 858421 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.1643. Min Act: -0.0000

Data Index: 1310401 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.1682. Min Act: -0.0000

Data Index: 696536 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.1685. Min Act: -0.0000

Data Index: 1249528 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.3051. Min Range: -0.3051

Max Act: 0.1512. Min Act: -0.0000

Data Index: 808797 (C4 (Web Text))

Max Activating Token Index: 384