Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1156 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0922. Min Range: -1.0922

Max Act: 1.0922. Min Act: -0.0001

Data Index: 682453 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 1.0922. Min Range: -1.0922

Max Act: 1.0017. Min Act: -0.0001

Data Index: 383216 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.9682. Min Act: -0.0001

Data Index: 1134060 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.8707. Min Act: -0.0001

Data Index: 836333 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.8910. Min Act: -0.0001

Data Index: 366773 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.9541. Min Act: -0.0001

Data Index: 583655 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.9466. Min Act: -0.0001

Data Index: 945872 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.8862. Min Act: -0.0001

Data Index: 1286818 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.7793. Min Act: -0.0001

Data Index: 728800 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.9008. Min Act: -0.0001

Data Index: 907198 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.8629. Min Act: -0.0001

Data Index: 822997 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.9174. Min Act: -0.0001

Data Index: 4754 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.8696. Min Act: -0.0001

Data Index: 23972 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.7904. Min Act: -0.0001

Data Index: 161236 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.7581. Min Act: -0.0001

Data Index: 883151 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.8245. Min Act: -0.0001

Data Index: 675493 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.8496. Min Act: -0.0001

Data Index: 665392 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.8003. Min Act: -0.0001

Data Index: 449117 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.8398. Min Act: -0.0001

Data Index: 71405 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.8663. Min Act: -0.0001

Data Index: 63413 (C4 (Web Text))

Max Activating Token Index: 708