Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1401 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1236. Min Act: -0.0002

Data Index: 1210057 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1270. Min Act: -0.0002

Data Index: 572375 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1054. Min Act: -0.0002

Data Index: 164952 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1203. Min Act: -0.0002

Data Index: 350711 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1156. Min Act: -0.0002

Data Index: 122998 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1098. Min Act: -0.0002

Data Index: 863685 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1168. Min Act: -0.0002

Data Index: 867836 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1088. Min Act: -0.0002

Data Index: 966678 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1096. Min Act: -0.0002

Data Index: 769588 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1054. Min Act: -0.0002

Data Index: 421938 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1033. Min Act: -0.0002

Data Index: 1055828 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1023. Min Act: -0.0002

Data Index: 190033 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0974. Min Act: -0.0002

Data Index: 1339532 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1031. Min Act: -0.0002

Data Index: 1021202 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0943. Min Act: -0.0002

Data Index: 1335089 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1039. Min Act: -0.0002

Data Index: 1350878 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1107. Min Act: -0.0002

Data Index: 879513 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0983. Min Act: -0.0002

Data Index: 1076163 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0980. Min Act: -0.0002

Data Index: 309822 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0935. Min Act: -0.0002

Data Index: 852419 (C4 (Web Text))

Max Activating Token Index: 140