Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4104 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7572. Min Range: -4.7572

Max Act: 4.7522. Min Act: -0.0000

Data Index: 75458 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 4.7572. Min Range: -4.7572

Max Act: 4.7572. Min Act: -0.0000

Data Index: 1123589 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 4.7572. Min Range: -4.7572

Max Act: 4.6602. Min Act: -0.0000

Data Index: 333065 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 4.7572. Min Range: -4.7572

Max Act: 4.7477. Min Act: -0.0000

Data Index: 69113 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 4.7572. Min Range: -4.7572

Max Act: 4.2307. Min Act: -0.0000

Data Index: 1303768 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 4.7572. Min Range: -4.7572

Max Act: 4.2449. Min Act: -0.0000

Data Index: 386579 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 4.7572. Min Range: -4.7572

Max Act: 4.3308. Min Act: -0.0000

Data Index: 657239 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 4.7572. Min Range: -4.7572

Max Act: 4.3319. Min Act: -0.0000

Data Index: 1015313 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 4.7572. Min Range: -4.7572

Max Act: 3.9137. Min Act: -0.0000

Data Index: 1127594 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 4.7572. Min Range: -4.7572

Max Act: 4.2348. Min Act: -0.0000

Data Index: 343821 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 4.7572. Min Range: -4.7572

Max Act: 4.2035. Min Act: -0.0000

Data Index: 713770 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 4.7572. Min Range: -4.7572

Max Act: 4.2119. Min Act: -0.0000

Data Index: 876778 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 4.7572. Min Range: -4.7572

Max Act: 3.6938. Min Act: -0.0000

Data Index: 602743 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 4.7572. Min Range: -4.7572

Max Act: 4.1932. Min Act: -0.0000

Data Index: 621111 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 4.7572. Min Range: -4.7572

Max Act: 4.1840. Min Act: -0.0000

Data Index: 592424 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 4.7572. Min Range: -4.7572

Max Act: 3.6738. Min Act: -0.0000

Data Index: 60232 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 4.7572. Min Range: -4.7572

Max Act: 3.7027. Min Act: -0.0000

Data Index: 135163 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 4.7572. Min Range: -4.7572

Max Act: 4.0333. Min Act: -0.0000

Data Index: 32844 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 4.7572. Min Range: -4.7572

Max Act: 3.5674. Min Act: -0.0000

Data Index: 376906 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 4.7572. Min Range: -4.7572

Max Act: 3.8533. Min Act: -0.0000

Data Index: 1067177 (C4 (Web Text))

Max Activating Token Index: 1011