Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1049 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1981. Min Act: -0.0006

Data Index: 1303668 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.2148. Min Act: -0.0006

Data Index: 959722 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1932. Min Act: -0.0006

Data Index: 210569 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.2053. Min Act: -0.0006

Data Index: 180651 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.2019. Min Act: -0.0006

Data Index: 668732 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1957. Min Act: -0.0006

Data Index: 832399 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1871. Min Act: -0.0006

Data Index: 878712 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1851. Min Act: -0.0006

Data Index: 341398 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1998. Min Act: -0.0006

Data Index: 1045232 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1849. Min Act: -0.0006

Data Index: 1012025 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1988. Min Act: -0.0006

Data Index: 549690 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1836. Min Act: -0.0006

Data Index: 962229 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1819. Min Act: -0.0006

Data Index: 923661 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1806. Min Act: -0.0006

Data Index: 193724 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1674. Min Act: -0.0006

Data Index: 107251 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1729. Min Act: -0.0006

Data Index: 932039 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1778. Min Act: -0.0006

Data Index: 1002503 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1841. Min Act: -0.0006

Data Index: 75826 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1836. Min Act: -0.0006

Data Index: 1111654 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1910. Min Act: -0.0006

Data Index: 289560 (C4 (Web Text))

Max Activating Token Index: 416