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

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

Neuron 2217 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.8998. Min Act: -0.0000

Data Index: 187315 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 4.8998. Min Range: -4.8998

Max Act: 3.7298. Min Act: -0.0001

Data Index: 330951 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.3263. Min Act: -0.0000

Data Index: 450213 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 4.8998. Min Range: -4.8998

Max Act: 4.0087. Min Act: -0.0001

Data Index: 858994 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 4.8998. Min Range: -4.8998

Max Act: 3.8810. Min Act: -0.0000

Data Index: 573298 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 4.8998. Min Range: -4.8998

Max Act: 3.7065. Min Act: -0.0000

Data Index: 702664 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 4.8998. Min Range: -4.8998

Max Act: 3.6851. Min Act: -0.0001

Data Index: 805276 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 4.8998. Min Range: -4.8998

Max Act: 3.7693. Min Act: -0.0001

Data Index: 704029 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 4.8998. Min Range: -4.8998

Max Act: 3.7059. Min Act: -0.0001

Data Index: 593347 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 4.8998. Min Range: -4.8998

Max Act: 3.4525. Min Act: -0.0001

Data Index: 346912 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 4.8998. Min Range: -4.8998

Max Act: 3.3610. Min Act: -0.0001

Data Index: 294562 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 4.8998. Min Range: -4.8998

Max Act: 3.1955. Min Act: -0.0001

Data Index: 1357899 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 4.8998. Min Range: -4.8998

Max Act: 3.6151. Min Act: -0.0000

Data Index: 159637 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 4.8998. Min Range: -4.8998

Max Act: 3.4807. Min Act: -0.0000

Data Index: 613170 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 4.8998. Min Range: -4.8998

Max Act: 3.6407. Min Act: -0.0001

Data Index: 1328413 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 4.8998. Min Range: -4.8998

Max Act: 3.1586. Min Act: -0.0000

Data Index: 776427 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 4.8998. Min Range: -4.8998

Max Act: 3.3395. Min Act: -0.0000

Data Index: 1137103 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 4.8998. Min Range: -4.8998

Max Act: 2.6515. Min Act: -0.0000

Data Index: 1248936 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 4.8998. Min Range: -4.8998

Max Act: 3.3133. Min Act: -0.0000

Data Index: 517963 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 4.8998. Min Range: -4.8998

Max Act: 3.2411. Min Act: -0.0001

Data Index: 1031340 (C4 (Web Text))

Max Activating Token Index: 754