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

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

Neuron 567 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2510. Min Range: -1.2510

Max Act: 1.2510. Min Act: -0.0000

Data Index: 55964 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 1.2510. Min Range: -1.2510

Max Act: 1.0792. Min Act: -0.0000

Data Index: 986545 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.8798. Min Act: -0.0000

Data Index: 959567 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1059268 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1334150 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.6657. Min Act: -0.0000

Data Index: 708131 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.6828. Min Act: -0.0000

Data Index: 1232098 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.6886. Min Act: -0.0000

Data Index: 681074 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.6527. Min Act: -0.0000

Data Index: 227546 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1045087 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.6945. Min Act: -0.0000

Data Index: 974407 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.6410. Min Act: -0.0000

Data Index: 1339290 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.6683. Min Act: -0.0000

Data Index: 931301 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.6344. Min Act: -0.0000

Data Index: 422206 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.6734. Min Act: -0.0000

Data Index: 71225 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.6386. Min Act: -0.0000

Data Index: 33632 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.6527. Min Act: -0.0000

Data Index: 915393 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.6497. Min Act: -0.0000

Data Index: 1237508 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.6512. Min Act: -0.0000

Data Index: 81788 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.6327. Min Act: -0.0000

Data Index: 221228 (C4 (Web Text))

Max Activating Token Index: 204