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

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

Neuron 3382 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0142. Min Range: -1.0142

Max Act: 1.0142. Min Act: -0.0000

Data Index: 1036856 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.9221. Min Act: -0.0000

Data Index: 844029 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.8550. Min Act: -0.0001

Data Index: 493733 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.9154. Min Act: -0.0000

Data Index: 859107 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.8736. Min Act: -0.0000

Data Index: 163370 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.8594. Min Act: -0.0001

Data Index: 961898 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.8019. Min Act: -0.0001

Data Index: 870410 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.8697. Min Act: -0.0000

Data Index: 174711 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.8872. Min Act: -0.0000

Data Index: 441029 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.8237. Min Act: -0.0001

Data Index: 682908 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.7463. Min Act: -0.0001

Data Index: 1234755 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.7886. Min Act: -0.0000

Data Index: 296131 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.7806. Min Act: -0.0000

Data Index: 1240583 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.7904. Min Act: -0.0000

Data Index: 605369 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.7411. Min Act: -0.0000

Data Index: 1109583 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.7313. Min Act: -0.0000

Data Index: 282900 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.7511. Min Act: -0.0001

Data Index: 825118 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1282251 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.7197. Min Act: -0.0000

Data Index: 943231 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 1.0142. Min Range: -1.0142

Max Act: 0.7516. Min Act: -0.0000

Data Index: 80278 (C4 (Web Text))

Max Activating Token Index: 830