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

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

Neuron 2655 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4050. Min Range: -2.4050

Max Act: 2.3056. Min Act: -0.0000

Data Index: 854959 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 2.4050. Min Range: -2.4050

Max Act: 2.4050. Min Act: -0.0000

Data Index: 693812 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 2.4050. Min Range: -2.4050

Max Act: 2.3792. Min Act: -0.0000

Data Index: 590778 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 2.4050. Min Range: -2.4050

Max Act: 2.2729. Min Act: -0.0000

Data Index: 1337917 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 2.4050. Min Range: -2.4050

Max Act: 2.2113. Min Act: -0.0000

Data Index: 1476511 (Python Code)

Max Activating Token Index: 386

Text #5

Max Range: 2.4050. Min Range: -2.4050

Max Act: 2.0600. Min Act: -0.0000

Data Index: 614539 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 2.4050. Min Range: -2.4050

Max Act: 2.0107. Min Act: -0.0000

Data Index: 1238563 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 2.4050. Min Range: -2.4050

Max Act: 2.2338. Min Act: -0.0000

Data Index: 776921 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 2.4050. Min Range: -2.4050

Max Act: 2.0992. Min Act: -0.0000

Data Index: 602933 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 2.4050. Min Range: -2.4050

Max Act: 2.0980. Min Act: -0.0000

Data Index: 1150933 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 2.4050. Min Range: -2.4050

Max Act: 1.9369. Min Act: -0.0000

Data Index: 165946 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 2.4050. Min Range: -2.4050

Max Act: 1.9788. Min Act: -0.0000

Data Index: 557506 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 2.4050. Min Range: -2.4050

Max Act: 2.0744. Min Act: -0.0000

Data Index: 1466553 (Python Code)

Max Activating Token Index: 231

Text #13

Max Range: 2.4050. Min Range: -2.4050

Max Act: 2.0575. Min Act: -0.0000

Data Index: 1127289 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 2.4050. Min Range: -2.4050

Max Act: 2.0505. Min Act: -0.0000

Data Index: 793483 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 2.4050. Min Range: -2.4050

Max Act: 1.8109. Min Act: -0.0000

Data Index: 128232 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 2.4050. Min Range: -2.4050

Max Act: 1.9053. Min Act: -0.0000

Data Index: 544889 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 2.4050. Min Range: -2.4050

Max Act: 1.8379. Min Act: -0.0000

Data Index: 1000428 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 2.4050. Min Range: -2.4050

Max Act: 1.7384. Min Act: -0.0000

Data Index: 1279960 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 2.4050. Min Range: -2.4050

Max Act: 1.7142. Min Act: -0.0000

Data Index: 1582859 (Python Code)

Max Activating Token Index: 719