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

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

Neuron 2113 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.3124. Min Act: -0.0001

Data Index: 436663 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2955. Min Act: -0.0001

Data Index: 489066 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.3089. Min Act: -0.0000

Data Index: 452825 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.3135. Min Act: -0.0001

Data Index: 77230 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2995. Min Act: -0.0001

Data Index: 562764 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.3172. Min Act: -0.0000

Data Index: 176237 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.3260. Min Act: -0.0000

Data Index: 79430 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.3259. Min Act: -0.0001

Data Index: 571378 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2716. Min Act: -0.0001

Data Index: 939790 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.3026. Min Act: -0.0001

Data Index: 849944 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.3230. Min Act: -0.0000

Data Index: 800131 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.3221. Min Act: -0.0001

Data Index: 1096631 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1216419 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.3203. Min Act: -0.0000

Data Index: 518161 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.3017. Min Act: -0.0000

Data Index: 108636 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.3012. Min Act: -0.0001

Data Index: 617502 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2990. Min Act: -0.0001

Data Index: 1139848 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2595. Min Act: -0.0001

Data Index: 407570 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2807. Min Act: -0.0000

Data Index: 352708 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.3260. Min Range: -0.3260

Max Act: 0.2787. Min Act: -0.0000

Data Index: 205723 (C4 (Web Text))

Max Activating Token Index: 837