Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2393 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.2904. Min Act: -0.0001

Data Index: 1073067 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0784. Min Act: -0.0001

Data Index: 989762 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0650. Min Act: -0.0001

Data Index: 396712 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0040. Min Act: -0.0001

Data Index: 817772 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 1.2904. Min Range: -1.2904

Max Act: 0.9322. Min Act: -0.0001

Data Index: 584853 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 1.2904. Min Range: -1.2904

Max Act: 0.9811. Min Act: -0.0001

Data Index: 1248766 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 1.2904. Min Range: -1.2904

Max Act: 0.9422. Min Act: -0.0001

Data Index: 263173 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 1.2904. Min Range: -1.2904

Max Act: 0.9354. Min Act: -0.0001

Data Index: 310194 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 1.2904. Min Range: -1.2904

Max Act: 0.9620. Min Act: -0.0001

Data Index: 794835 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 1.2904. Min Range: -1.2904

Max Act: 0.8925. Min Act: -0.0001

Data Index: 1117325 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 1.2904. Min Range: -1.2904

Max Act: 0.8817. Min Act: -0.0001

Data Index: 191261 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 1.2904. Min Range: -1.2904

Max Act: 0.9134. Min Act: -0.0001

Data Index: 1162358 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 1.2904. Min Range: -1.2904

Max Act: 0.9124. Min Act: -0.0001

Data Index: 604820 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 1.2904. Min Range: -1.2904

Max Act: 0.9064. Min Act: -0.0001

Data Index: 626357 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 1.2904. Min Range: -1.2904

Max Act: 0.9268. Min Act: -0.0001

Data Index: 1339695 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 1.2904. Min Range: -1.2904

Max Act: 0.8931. Min Act: -0.0001

Data Index: 524087 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 1.2904. Min Range: -1.2904

Max Act: 0.8819. Min Act: -0.0001

Data Index: 1197285 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 1.2904. Min Range: -1.2904

Max Act: 0.8681. Min Act: -0.0001

Data Index: 441673 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 1.2904. Min Range: -1.2904

Max Act: 0.9053. Min Act: -0.0001

Data Index: 1220694 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 1.2904. Min Range: -1.2904

Max Act: 0.8814. Min Act: -0.0001

Data Index: 72347 (C4 (Web Text))

Max Activating Token Index: 858