Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 534 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.6216. Min Act: -0.0001

Data Index: 600782 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.2974. Min Act: -0.0001

Data Index: 80946 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.3033. Min Act: -0.0001

Data Index: 297931 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.1997. Min Act: -0.0001

Data Index: 263336 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.2686. Min Act: -0.0001

Data Index: 9678 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.1275. Min Act: -0.0001

Data Index: 459942 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.1304. Min Act: -0.0001

Data Index: 1173355 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.1976. Min Act: -0.0001

Data Index: 888192 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.0995. Min Act: -0.0001

Data Index: 445723 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.2298. Min Act: -0.0001

Data Index: 1235402 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.1090. Min Act: -0.0001

Data Index: 1029038 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.1802. Min Act: -0.0001

Data Index: 925898 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.0717. Min Act: -0.0001

Data Index: 644769 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.1296. Min Act: -0.0001

Data Index: 1217314 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.0714. Min Act: -0.0001

Data Index: 243511 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.1558. Min Act: -0.0001

Data Index: 209965 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.0573. Min Act: -0.0001

Data Index: 1065643 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.1095. Min Act: -0.0001

Data Index: 450773 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.0520. Min Act: -0.0001

Data Index: 982493 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 1.6216. Min Range: -1.6216

Max Act: 1.0779. Min Act: -0.0001

Data Index: 954434 (C4 (Web Text))

Max Activating Token Index: 1017