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

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

Neuron 5065 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: 4.6018. Min Range: -4.6018

Max Act: 4.6018. Min Act: -0.0000

Data Index: 506161 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 4.6018. Min Range: -4.6018

Max Act: 4.1787. Min Act: -0.0000

Data Index: 908929 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 4.6018. Min Range: -4.6018

Max Act: 3.6601. Min Act: -0.0000

Data Index: 1061206 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 4.6018. Min Range: -4.6018

Max Act: 3.4319. Min Act: -0.0000

Data Index: 580216 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 4.6018. Min Range: -4.6018

Max Act: 3.4700. Min Act: -0.0000

Data Index: 1332171 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 4.6018. Min Range: -4.6018

Max Act: 3.9953. Min Act: -0.0000

Data Index: 1415261 (Python Code)

Max Activating Token Index: 313

Text #6

Max Range: 4.6018. Min Range: -4.6018

Max Act: 3.6666. Min Act: -0.0000

Data Index: 1031145 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 4.6018. Min Range: -4.6018

Max Act: 3.6184. Min Act: -0.0000

Data Index: 99171 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 4.6018. Min Range: -4.6018

Max Act: 3.4839. Min Act: -0.0000

Data Index: 785907 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 4.6018. Min Range: -4.6018

Max Act: 3.3942. Min Act: -0.0000

Data Index: 1111402 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 4.6018. Min Range: -4.6018

Max Act: 3.3511. Min Act: -0.0000

Data Index: 1549799 (Python Code)

Max Activating Token Index: 594

Text #11

Max Range: 4.6018. Min Range: -4.6018

Max Act: 3.4387. Min Act: -0.0000

Data Index: 1632544 (Python Code)

Max Activating Token Index: 878

Text #12

Max Range: 4.6018. Min Range: -4.6018

Max Act: 3.4613. Min Act: -0.0000

Data Index: 1181741 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 4.6018. Min Range: -4.6018

Max Act: 3.2382. Min Act: -0.0000

Data Index: 483922 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 4.6018. Min Range: -4.6018

Max Act: 3.2398. Min Act: -0.0000

Data Index: 1024691 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 4.6018. Min Range: -4.6018

Max Act: 3.3275. Min Act: -0.0000

Data Index: 751410 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 4.6018. Min Range: -4.6018

Max Act: 3.4916. Min Act: -0.0000

Data Index: 318873 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 4.6018. Min Range: -4.6018

Max Act: 3.4419. Min Act: -0.0000

Data Index: 633576 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 4.6018. Min Range: -4.6018

Max Act: 3.2997. Min Act: -0.0000

Data Index: 1165185 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 4.6018. Min Range: -4.6018

Max Act: 3.5662. Min Act: -0.0000

Data Index: 875248 (C4 (Web Text))

Max Activating Token Index: 474