Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2595 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.4302. Min Act: -0.0000

Data Index: 541415 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.3644. Min Act: -0.0000

Data Index: 712443 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.3135. Min Act: -0.0000

Data Index: 1220163 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2921. Min Act: -0.0000

Data Index: 607984 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2916. Min Act: -0.0000

Data Index: 156753 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1292252 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2859. Min Act: -0.0000

Data Index: 35595 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2646. Min Act: -0.0000

Data Index: 83761 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2832. Min Act: -0.0000

Data Index: 567248 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2880. Min Act: -0.0000

Data Index: 618893 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1306588 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2660. Min Act: -0.0000

Data Index: 466617 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2556. Min Act: -0.0000

Data Index: 324649 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2713. Min Act: -0.0000

Data Index: 215098 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2582. Min Act: -0.0000

Data Index: 1284143 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2569. Min Act: -0.0000

Data Index: 12340 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2575. Min Act: -0.0000

Data Index: 871211 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1249017 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2721. Min Act: -0.0000

Data Index: 242854 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.2641. Min Act: -0.0000

Data Index: 94819 (C4 (Web Text))

Max Activating Token Index: 232