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

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

Neuron 1529 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0284. Min Range: -1.0284

Max Act: 1.0284. Min Act: -0.0001

Data Index: 1010206 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.9503. Min Act: -0.0001

Data Index: 12798 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.9289. Min Act: -0.0001

Data Index: 115413 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.9150. Min Act: -0.0001

Data Index: 49570 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.8848. Min Act: -0.0001

Data Index: 1341649 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 1.0284. Min Range: -1.0284

Max Act: 1.0070. Min Act: -0.0001

Data Index: 1011730 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.9026. Min Act: -0.0001

Data Index: 1067565 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.9739. Min Act: -0.0001

Data Index: 1333831 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.7478. Min Act: -0.0001

Data Index: 1301661 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.8447. Min Act: -0.0001

Data Index: 1205240 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.8378. Min Act: -0.0001

Data Index: 1152330 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.8228. Min Act: -0.0001

Data Index: 256567 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.8513. Min Act: -0.0001

Data Index: 1310256 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.7764. Min Act: -0.0001

Data Index: 22117 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.8104. Min Act: -0.0001

Data Index: 1131044 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.8940. Min Act: -0.0001

Data Index: 1298677 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.8082. Min Act: -0.0001

Data Index: 523335 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.7536. Min Act: -0.0001

Data Index: 273674 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.8167. Min Act: -0.0001

Data Index: 1323083 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 1.0284. Min Range: -1.0284

Max Act: 0.8178. Min Act: -0.0001

Data Index: 166616 (C4 (Web Text))

Max Activating Token Index: 897