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

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

Neuron 978 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: 3.5730. Min Range: -3.5730

Max Act: 3.5730. Min Act: -0.0000

Data Index: 898690 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 3.5730. Min Range: -3.5730

Max Act: 3.2404. Min Act: -0.0000

Data Index: 59247 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 3.5730. Min Range: -3.5730

Max Act: 3.1467. Min Act: -0.0000

Data Index: 89527 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.6362. Min Act: -0.0000

Data Index: 58023 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.6253. Min Act: -0.0000

Data Index: 1232436 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.7529. Min Act: -0.0000

Data Index: 255633 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.4305. Min Act: -0.0000

Data Index: 14418 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.3561. Min Act: -0.0000

Data Index: 1358580 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.1746. Min Act: -0.0000

Data Index: 26249 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 3.5730. Min Range: -3.5730

Max Act: 1.9194. Min Act: -0.0000

Data Index: 1585671 (Python Code)

Max Activating Token Index: 207

Text #10

Max Range: 3.5730. Min Range: -3.5730

Max Act: 1.9795. Min Act: -0.0000

Data Index: 683066 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.1900. Min Act: -0.0000

Data Index: 909091 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.4943. Min Act: -0.0000

Data Index: 629803 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.0152. Min Act: -0.0000

Data Index: 1314070 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 3.5730. Min Range: -3.5730

Max Act: 1.8995. Min Act: -0.0000

Data Index: 803752 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.0590. Min Act: -0.0000

Data Index: 640473 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 3.5730. Min Range: -3.5730

Max Act: 1.8740. Min Act: -0.0000

Data Index: 1493678 (Python Code)

Max Activating Token Index: 804

Text #17

Max Range: 3.5730. Min Range: -3.5730

Max Act: 1.9291. Min Act: -0.0000

Data Index: 851746 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 3.5730. Min Range: -3.5730

Max Act: 1.9551. Min Act: -0.0000

Data Index: 103769 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 3.5730. Min Range: -3.5730

Max Act: 1.8440. Min Act: -0.0000

Data Index: 1078973 (C4 (Web Text))

Max Activating Token Index: 542