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

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

Neuron 1917 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.7108. Min Act: -0.0001

Data Index: 838936 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.8499. Min Act: -0.0001

Data Index: 748667 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.7810. Min Act: -0.0001

Data Index: 861523 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.7741. Min Act: -0.0001

Data Index: 1283010 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.6247. Min Act: -0.0001

Data Index: 682211 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.6693. Min Act: -0.0001

Data Index: 278058 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.6872. Min Act: -0.0001

Data Index: 247612 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.6375. Min Act: -0.0001

Data Index: 846563 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.6861. Min Act: -0.0001

Data Index: 99790 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.6885. Min Act: -0.0001

Data Index: 247110 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.5953. Min Act: -0.0001

Data Index: 28249 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.7579. Min Act: -0.0001

Data Index: 640 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.5461. Min Act: -0.0001

Data Index: 1137236 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.6541. Min Act: -0.0001

Data Index: 732479 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.6154. Min Act: -0.0001

Data Index: 1118332 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.5980. Min Act: -0.0001

Data Index: 95127 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.5973. Min Act: -0.0001

Data Index: 1306619 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.5566. Min Act: -0.0001

Data Index: 1228324 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.5715. Min Act: -0.0001

Data Index: 1273392 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.6417. Min Act: -0.0001

Data Index: 245525 (C4 (Web Text))

Max Activating Token Index: 52