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

Dataset: The Pile

Neuron 3913 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1262499 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.4121. Min Act: -0.0000

Data Index: 842927 (The Pile)

Max Activating Token Index: 388

Text #2

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3626. Min Act: -0.0000

Data Index: 1780944 (The Pile)

Max Activating Token Index: 643

Text #3

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1011760 (The Pile)

Max Activating Token Index: 458

Text #4

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3695. Min Act: -0.0000

Data Index: 570077 (The Pile)

Max Activating Token Index: 109

Text #5

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3521. Min Act: -0.0000

Data Index: 113756 (The Pile)

Max Activating Token Index: 254

Text #6

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3354. Min Act: -0.0000

Data Index: 795560 (The Pile)

Max Activating Token Index: 836

Text #7

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1079459 (The Pile)

Max Activating Token Index: 150

Text #8

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3458. Min Act: -0.0000

Data Index: 1222341 (The Pile)

Max Activating Token Index: 280

Text #9

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3084. Min Act: -0.0000

Data Index: 356082 (The Pile)

Max Activating Token Index: 623

Text #10

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3228. Min Act: -0.0000

Data Index: 776987 (The Pile)

Max Activating Token Index: 655

Text #11

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1402120 (The Pile)

Max Activating Token Index: 683

Text #12

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3057. Min Act: -0.0000

Data Index: 346035 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3283. Min Act: -0.0000

Data Index: 8447 (The Pile)

Max Activating Token Index: 284

Text #14

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3147. Min Act: -0.0000

Data Index: 1805664 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1259178 (The Pile)

Max Activating Token Index: 96

Text #16

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1454791 (The Pile)

Max Activating Token Index: 598

Text #17

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3010. Min Act: -0.0000

Data Index: 258297 (The Pile)

Max Activating Token Index: 610

Text #18

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3093. Min Act: -0.0000

Data Index: 495855 (The Pile)

Max Activating Token Index: 154

Text #19

Max Range: 0.4511. Min Range: -0.4511

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1561270 (The Pile)

Max Activating Token Index: 967