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

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

Neuron 699 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8812. Min Range: -3.8812

Max Act: 3.8812. Min Act: -0.0000

Data Index: 928966 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 3.8812. Min Range: -3.8812

Max Act: 3.7596. Min Act: -0.0000

Data Index: 568967 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 3.8812. Min Range: -3.8812

Max Act: 3.5140. Min Act: -0.0000

Data Index: 1101924 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 3.8812. Min Range: -3.8812

Max Act: 3.5800. Min Act: -0.0000

Data Index: 1012805 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 3.8812. Min Range: -3.8812

Max Act: 3.5364. Min Act: -0.0000

Data Index: 971627 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 3.8812. Min Range: -3.8812

Max Act: 3.4056. Min Act: -0.0000

Data Index: 132784 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 3.8812. Min Range: -3.8812

Max Act: 3.2603. Min Act: -0.0000

Data Index: 235311 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 3.8812. Min Range: -3.8812

Max Act: 3.4978. Min Act: -0.0000

Data Index: 1175577 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 3.8812. Min Range: -3.8812

Max Act: 3.3211. Min Act: -0.0000

Data Index: 1134466 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 3.8812. Min Range: -3.8812

Max Act: 3.1114. Min Act: -0.0000

Data Index: 949550 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 3.8812. Min Range: -3.8812

Max Act: 3.1091. Min Act: -0.0000

Data Index: 610426 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 3.8812. Min Range: -3.8812

Max Act: 3.2455. Min Act: -0.0000

Data Index: 303872 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 3.8812. Min Range: -3.8812

Max Act: 3.1933. Min Act: -0.0001

Data Index: 605769 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 3.8812. Min Range: -3.8812

Max Act: 3.1118. Min Act: -0.0001

Data Index: 379968 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 3.8812. Min Range: -3.8812

Max Act: 3.1113. Min Act: -0.0000

Data Index: 680597 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 3.8812. Min Range: -3.8812

Max Act: 2.9446. Min Act: -0.0000

Data Index: 126361 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 3.8812. Min Range: -3.8812

Max Act: 3.0897. Min Act: -0.0000

Data Index: 184781 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 3.8812. Min Range: -3.8812

Max Act: 3.2241. Min Act: -0.0001

Data Index: 319091 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 3.8812. Min Range: -3.8812

Max Act: 3.0076. Min Act: -0.0001

Data Index: 1031587 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 3.8812. Min Range: -3.8812

Max Act: 2.9983. Min Act: -0.0000

Data Index: 1088755 (C4 (Web Text))

Max Activating Token Index: 533