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

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

Neuron 2042 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: 1.2641. Min Range: -1.2641

Max Act: 1.2641. Min Act: -0.0001

Data Index: 354302 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.2101. Min Act: -0.0001

Data Index: 639965 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.2105. Min Act: -0.0001

Data Index: 991950 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.2083. Min Act: -0.0001

Data Index: 527186 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1883. Min Act: -0.0001

Data Index: 762553 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1609. Min Act: -0.0001

Data Index: 757012 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1442. Min Act: -0.0001

Data Index: 982279 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1499. Min Act: -0.0001

Data Index: 1310205 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1500. Min Act: -0.0001

Data Index: 34821 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1007. Min Act: -0.0001

Data Index: 711340 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1364. Min Act: -0.0001

Data Index: 665686 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1271. Min Act: -0.0001

Data Index: 1214430 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1314. Min Act: -0.0001

Data Index: 1108925 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0898. Min Act: -0.0001

Data Index: 87814 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0857. Min Act: -0.0001

Data Index: 1271290 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1556. Min Act: -0.0001

Data Index: 883874 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0494. Min Act: -0.0001

Data Index: 951083 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0866. Min Act: -0.0001

Data Index: 642441 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0897. Min Act: -0.0001

Data Index: 257234 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0449. Min Act: -0.0001

Data Index: 1206404 (C4 (Web Text))

Max Activating Token Index: 163