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

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

Neuron 4005 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: 0.4791. Min Range: -0.4791

Max Act: 0.4791. Min Act: -0.0000

Data Index: 865240 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.4423. Min Act: -0.0000

Data Index: 168791 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.4062. Min Act: -0.0000

Data Index: 293704 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.3777. Min Act: -0.0000

Data Index: 109759 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.3571. Min Act: -0.0000

Data Index: 515679 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.3142. Min Act: -0.0000

Data Index: 1283896 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.2971. Min Act: -0.0000

Data Index: 1178831 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.2995. Min Act: -0.0000

Data Index: 886065 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.3067. Min Act: -0.0000

Data Index: 994272 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.3027. Min Act: -0.0000

Data Index: 1407689 (Python Code)

Max Activating Token Index: 104

Text #10

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.3004. Min Act: -0.0000

Data Index: 851016 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1243731 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.2642. Min Act: -0.0000

Data Index: 944242 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.2881. Min Act: -0.0000

Data Index: 1491601 (Python Code)

Max Activating Token Index: 463

Text #14

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.2678. Min Act: -0.0000

Data Index: 236007 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.2839. Min Act: -0.0000

Data Index: 883685 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.2716. Min Act: -0.0000

Data Index: 700395 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1581607 (Python Code)

Max Activating Token Index: 787

Text #18

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.2718. Min Act: -0.0000

Data Index: 531709 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1271268 (C4 (Web Text))

Max Activating Token Index: 200