Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1721 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5093. Min Range: -2.5093

Max Act: 2.5093. Min Act: -0.0000

Data Index: 345172 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 2.5093. Min Range: -2.5093

Max Act: 2.1994. Min Act: -0.0000

Data Index: 1096235 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 2.5093. Min Range: -2.5093

Max Act: 2.4218. Min Act: -0.0000

Data Index: 10983 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 2.5093. Min Range: -2.5093

Max Act: 2.2286. Min Act: -0.0000

Data Index: 820872 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 2.5093. Min Range: -2.5093

Max Act: 1.9555. Min Act: -0.0000

Data Index: 162954 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 2.5093. Min Range: -2.5093

Max Act: 2.1179. Min Act: -0.0000

Data Index: 703086 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 2.5093. Min Range: -2.5093

Max Act: 2.1237. Min Act: 0.0000

Data Index: 561453 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 2.5093. Min Range: -2.5093

Max Act: 2.1730. Min Act: 0.0000

Data Index: 925539 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 2.5093. Min Range: -2.5093

Max Act: 2.0552. Min Act: -0.0000

Data Index: 18870 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 2.5093. Min Range: -2.5093

Max Act: 2.0174. Min Act: -0.0000

Data Index: 579848 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 2.5093. Min Range: -2.5093

Max Act: 2.1526. Min Act: -0.0000

Data Index: 383733 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 2.5093. Min Range: -2.5093

Max Act: 1.8706. Min Act: -0.0000

Data Index: 796707 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 2.5093. Min Range: -2.5093

Max Act: 1.9830. Min Act: -0.0000

Data Index: 1255912 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 2.5093. Min Range: -2.5093

Max Act: 1.9774. Min Act: 0.0000

Data Index: 1072476 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 2.5093. Min Range: -2.5093

Max Act: 1.9411. Min Act: 0.0000

Data Index: 459037 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 2.5093. Min Range: -2.5093

Max Act: 2.0476. Min Act: -0.0000

Data Index: 1332540 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 2.5093. Min Range: -2.5093

Max Act: 1.8303. Min Act: -0.0000

Data Index: 1329565 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 2.5093. Min Range: -2.5093

Max Act: 1.9259. Min Act: 0.0000

Data Index: 861437 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 2.5093. Min Range: -2.5093

Max Act: 1.9159. Min Act: -0.0000

Data Index: 155561 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 2.5093. Min Range: -2.5093

Max Act: 1.9099. Min Act: -0.0000

Data Index: 1323159 (C4 (Web Text))

Max Activating Token Index: 618