Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3824 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1931. Min Range: -1.1931

Max Act: 1.1928. Min Act: -0.0000

Data Index: 1358209 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 1.1931. Min Range: -1.1931

Max Act: 1.1625. Min Act: -0.0000

Data Index: 996100 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 1.1931. Min Range: -1.1931

Max Act: 1.1931. Min Act: -0.0000

Data Index: 1168420 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 1.1931. Min Range: -1.1931

Max Act: 1.0694. Min Act: -0.0000

Data Index: 616889 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 1.1931. Min Range: -1.1931

Max Act: 1.0252. Min Act: -0.0000

Data Index: 317816 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 1.1931. Min Range: -1.1931

Max Act: 1.0060. Min Act: -0.0000

Data Index: 659806 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.9885. Min Act: -0.0000

Data Index: 874993 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.9636. Min Act: -0.0000

Data Index: 431520 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.9817. Min Act: -0.0000

Data Index: 955329 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.9254. Min Act: -0.0000

Data Index: 373957 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.9643. Min Act: -0.0000

Data Index: 347660 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 1.1931. Min Range: -1.1931

Max Act: 1.0495. Min Act: -0.0000

Data Index: 680336 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.9156. Min Act: -0.0000

Data Index: 717171 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.9118. Min Act: -0.0000

Data Index: 844428 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.8729. Min Act: -0.0000

Data Index: 235930 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1220481 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.9522. Min Act: -0.0000

Data Index: 936907 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.8618. Min Act: -0.0000

Data Index: 1243904 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1210000 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 1.1931. Min Range: -1.1931

Max Act: 0.8766. Min Act: -0.0000

Data Index: 298163 (C4 (Web Text))

Max Activating Token Index: 492