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

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

Neuron 3891 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1084. Min Act: -0.0001

Data Index: 1149964 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1469465 (Python Code)

Max Activating Token Index: 783

Text #2

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1108. Min Act: -0.0001

Data Index: 913859 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1107. Min Act: -0.0001

Data Index: 1170672 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1141. Min Act: -0.0001

Data Index: 1310218 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1101. Min Act: -0.0001

Data Index: 1602476 (Python Code)

Max Activating Token Index: 1022

Text #6

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1093. Min Act: -0.0000

Data Index: 1138231 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1083081 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1092289 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1033. Min Act: -0.0001

Data Index: 1193282 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1036. Min Act: -0.0001

Data Index: 1251201 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1062. Min Act: -0.0001

Data Index: 1023745 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1540495 (Python Code)

Max Activating Token Index: 603

Text #13

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1018. Min Act: -0.0001

Data Index: 123103 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0977. Min Act: -0.0001

Data Index: 941839 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0967. Min Act: -0.0000

Data Index: 989429 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0966. Min Act: -0.0001

Data Index: 1506755 (Python Code)

Max Activating Token Index: 656

Text #17

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0933. Min Act: -0.0001

Data Index: 849343 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1031. Min Act: -0.0001

Data Index: 932434 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1025. Min Act: -0.0001

Data Index: 164139 (C4 (Web Text))

Max Activating Token Index: 690