Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2131 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3778. Min Act: -0.0001

Data Index: 1532451 (Python Code)

Max Activating Token Index: 555

Text #1

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3754. Min Act: -0.0001

Data Index: 1463063 (Python Code)

Max Activating Token Index: 174

Text #2

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3527. Min Act: -0.0001

Data Index: 1507333 (Python Code)

Max Activating Token Index: 976

Text #3

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3421. Min Act: -0.0001

Data Index: 1470579 (Python Code)

Max Activating Token Index: 394

Text #4

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3274. Min Act: -0.0001

Data Index: 1485018 (Python Code)

Max Activating Token Index: 215

Text #5

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3252. Min Act: -0.0001

Data Index: 1556007 (Python Code)

Max Activating Token Index: 475

Text #6

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3136. Min Act: -0.0001

Data Index: 1575456 (Python Code)

Max Activating Token Index: 767

Text #7

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3149. Min Act: -0.0001

Data Index: 1376251 (Python Code)

Max Activating Token Index: 49

Text #8

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3037. Min Act: -0.0001

Data Index: 687844 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2837. Min Act: -0.0001

Data Index: 1617675 (Python Code)

Max Activating Token Index: 376

Text #10

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2687. Min Act: -0.0001

Data Index: 1556651 (Python Code)

Max Activating Token Index: 343

Text #11

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3017. Min Act: -0.0001

Data Index: 1582693 (Python Code)

Max Activating Token Index: 355

Text #12

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3230. Min Act: -0.0001

Data Index: 198806 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2779. Min Act: -0.0001

Data Index: 1611828 (Python Code)

Max Activating Token Index: 639

Text #14

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2673. Min Act: -0.0001

Data Index: 1483825 (Python Code)

Max Activating Token Index: 488

Text #15

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2370. Min Act: -0.0001

Data Index: 1612568 (Python Code)

Max Activating Token Index: 685

Text #16

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2675. Min Act: -0.0001

Data Index: 1414306 (Python Code)

Max Activating Token Index: 287

Text #17

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2744. Min Act: -0.0001

Data Index: 1414022 (Python Code)

Max Activating Token Index: 452

Text #18

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2916. Min Act: -0.0001

Data Index: 1389644 (Python Code)

Max Activating Token Index: 250

Text #19

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.2595. Min Act: -0.0001

Data Index: 1486457 (Python Code)

Max Activating Token Index: 103