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

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

Neuron 2703 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5730. Min Range: -2.5730

Max Act: 2.5730. Min Act: -0.0000

Data Index: 127993 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 2.5730. Min Range: -2.5730

Max Act: 2.0835. Min Act: -0.0000

Data Index: 887054 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 2.5730. Min Range: -2.5730

Max Act: 2.1351. Min Act: -0.0000

Data Index: 539570 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 2.5730. Min Range: -2.5730

Max Act: 2.0346. Min Act: -0.0000

Data Index: 236487 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 2.5730. Min Range: -2.5730

Max Act: 1.7035. Min Act: -0.0000

Data Index: 892612 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 2.5730. Min Range: -2.5730

Max Act: 1.5430. Min Act: -0.0000

Data Index: 794064 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 2.5730. Min Range: -2.5730

Max Act: 1.4664. Min Act: -0.0000

Data Index: 1196568 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 2.5730. Min Range: -2.5730

Max Act: 1.4403. Min Act: -0.0000

Data Index: 1219159 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 2.5730. Min Range: -2.5730

Max Act: 1.3599. Min Act: -0.0000

Data Index: 719252 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 2.5730. Min Range: -2.5730

Max Act: 1.5014. Min Act: -0.0000

Data Index: 1266028 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 2.5730. Min Range: -2.5730

Max Act: 1.4763. Min Act: -0.0000

Data Index: 502784 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 2.5730. Min Range: -2.5730

Max Act: 1.3219. Min Act: -0.0000

Data Index: 10236 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 2.5730. Min Range: -2.5730

Max Act: 1.3594. Min Act: -0.0000

Data Index: 598153 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 2.5730. Min Range: -2.5730

Max Act: 1.3631. Min Act: -0.0000

Data Index: 878788 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 2.5730. Min Range: -2.5730

Max Act: 1.2741. Min Act: -0.0000

Data Index: 800114 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 2.5730. Min Range: -2.5730

Max Act: 1.3341. Min Act: -0.0000

Data Index: 14023 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 2.5730. Min Range: -2.5730

Max Act: 1.2632. Min Act: -0.0000

Data Index: 205192 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 2.5730. Min Range: -2.5730

Max Act: 1.2835. Min Act: -0.0000

Data Index: 544382 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 2.5730. Min Range: -2.5730

Max Act: 1.2231. Min Act: -0.0000

Data Index: 1325609 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 2.5730. Min Range: -2.5730

Max Act: 1.1932. Min Act: -0.0000

Data Index: 455638 (C4 (Web Text))

Max Activating Token Index: 371