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

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

Neuron 47 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1309. Min Act: -0.0003

Data Index: 261664 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1194. Min Act: -0.0003

Data Index: 574714 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1107. Min Act: -0.0003

Data Index: 1268897 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1106. Min Act: -0.0002

Data Index: 276644 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1083. Min Act: -0.0003

Data Index: 720264 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0983. Min Act: -0.0002

Data Index: 1082782 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0995. Min Act: -0.0003

Data Index: 483997 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0996. Min Act: -0.0003

Data Index: 1076124 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0988. Min Act: -0.0002

Data Index: 813202 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0952. Min Act: -0.0003

Data Index: 287840 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0944. Min Act: -0.0002

Data Index: 576544 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0901. Min Act: -0.0002

Data Index: 1077387 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.1019. Min Act: -0.0002

Data Index: 645752 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0950. Min Act: -0.0003

Data Index: 1193923 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0975. Min Act: -0.0003

Data Index: 336983 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0906. Min Act: -0.0002

Data Index: 554085 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0901. Min Act: -0.0003

Data Index: 317834 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0887. Min Act: -0.0002

Data Index: 232634 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0907. Min Act: -0.0003

Data Index: 867572 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.1309. Min Range: -0.1309

Max Act: 0.0938. Min Act: -0.0003

Data Index: 102636 (C4 (Web Text))

Max Activating Token Index: 544