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

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

Neuron 1490 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5689. Min Act: -0.0000

Data Index: 181907 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5642. Min Act: -0.0000

Data Index: 560710 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5597. Min Act: -0.0000

Data Index: 447753 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1017021 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5309. Min Act: -0.0000

Data Index: 176150 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5309. Min Act: -0.0000

Data Index: 923420 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5270. Min Act: -0.0000

Data Index: 1416921 (Python Code)

Max Activating Token Index: 1014

Text #7

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5312. Min Act: -0.0000

Data Index: 746173 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5107. Min Act: -0.0000

Data Index: 766448 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5080. Min Act: -0.0000

Data Index: 21603 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4743. Min Act: -0.0000

Data Index: 114755 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5266. Min Act: -0.0000

Data Index: 96710 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5577. Min Act: -0.0000

Data Index: 94100 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5177. Min Act: -0.0000

Data Index: 423717 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5178. Min Act: -0.0000

Data Index: 23453 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4959. Min Act: -0.0000

Data Index: 244414 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4963. Min Act: -0.0000

Data Index: 26796 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4941. Min Act: -0.0000

Data Index: 436930 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4918. Min Act: -0.0000

Data Index: 1287017 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1272359 (C4 (Web Text))

Max Activating Token Index: 623