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

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

Neuron 1202 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: 2.4824. Min Range: -2.4824

Max Act: 2.4824. Min Act: -0.0000

Data Index: 392878 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 2.4824. Min Range: -2.4824

Max Act: 2.4364. Min Act: -0.0001

Data Index: 181039 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 2.4824. Min Range: -2.4824

Max Act: 2.3132. Min Act: -0.0000

Data Index: 1157227 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 2.4824. Min Range: -2.4824

Max Act: 1.8569. Min Act: -0.0000

Data Index: 689006 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 2.4824. Min Range: -2.4824

Max Act: 2.1621. Min Act: -0.0000

Data Index: 274811 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 2.4824. Min Range: -2.4824

Max Act: 2.0569. Min Act: -0.0000

Data Index: 448959 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 2.4824. Min Range: -2.4824

Max Act: 2.1587. Min Act: -0.0000

Data Index: 369621 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 2.4824. Min Range: -2.4824

Max Act: 1.9956. Min Act: -0.0000

Data Index: 389661 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 2.4824. Min Range: -2.4824

Max Act: 1.9567. Min Act: -0.0000

Data Index: 1199653 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 2.4824. Min Range: -2.4824

Max Act: 2.0559. Min Act: -0.0000

Data Index: 771568 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 2.4824. Min Range: -2.4824

Max Act: 1.9112. Min Act: -0.0000

Data Index: 492305 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 2.4824. Min Range: -2.4824

Max Act: 1.9071. Min Act: -0.0000

Data Index: 578623 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 2.4824. Min Range: -2.4824

Max Act: 1.7296. Min Act: -0.0000

Data Index: 535878 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 2.4824. Min Range: -2.4824

Max Act: 1.8974. Min Act: -0.0000

Data Index: 125201 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 2.4824. Min Range: -2.4824

Max Act: 1.8475. Min Act: -0.0000

Data Index: 860148 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 2.4824. Min Range: -2.4824

Max Act: 1.8843. Min Act: -0.0000

Data Index: 1358802 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 2.4824. Min Range: -2.4824

Max Act: 1.6899. Min Act: -0.0000

Data Index: 1652 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 2.4824. Min Range: -2.4824

Max Act: 1.8343. Min Act: -0.0000

Data Index: 842449 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 2.4824. Min Range: -2.4824

Max Act: 1.7436. Min Act: -0.0000

Data Index: 228322 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 2.4824. Min Range: -2.4824

Max Act: 1.7330. Min Act: -0.0000

Data Index: 1242097 (C4 (Web Text))

Max Activating Token Index: 96