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

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

Neuron 4766 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.8075. Min Act: 0.0000

Data Index: 928317 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.5843. Min Act: -0.0000

Data Index: 625505 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.4804. Min Act: -0.0000

Data Index: 395633 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 1.8075. Min Range: -1.8075

Max Act: 0.8862. Min Act: -0.0000

Data Index: 883656 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 1.8075. Min Range: -1.8075

Max Act: 0.7678. Min Act: -0.0000

Data Index: 5995 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 1.8075. Min Range: -1.8075

Max Act: 0.6874. Min Act: -0.0000

Data Index: 330767 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 1.8075. Min Range: -1.8075

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1027993 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 1.8075. Min Range: -1.8075

Max Act: 0.6291. Min Act: -0.0000

Data Index: 14158 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 1.8075. Min Range: -1.8075

Max Act: 0.5907. Min Act: -0.0000

Data Index: 165675 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 1.8075. Min Range: -1.8075

Max Act: 0.5437. Min Act: 0.0001

Data Index: 76727 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 1.8075. Min Range: -1.8075

Max Act: 0.5069. Min Act: -0.0000

Data Index: 431657 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 1.8075. Min Range: -1.8075

Max Act: 0.4994. Min Act: -0.0000

Data Index: 276138 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 1.8075. Min Range: -1.8075

Max Act: 0.5321. Min Act: -0.0000

Data Index: 975006 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 1.8075. Min Range: -1.8075

Max Act: 0.5081. Min Act: -0.0000

Data Index: 19270 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 1.8075. Min Range: -1.8075

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1095293 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 1.8075. Min Range: -1.8075

Max Act: 0.4385. Min Act: -0.0000

Data Index: 89297 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 1.8075. Min Range: -1.8075

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1125170 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 1.8075. Min Range: -1.8075

Max Act: 0.4570. Min Act: -0.0000

Data Index: 643250 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 1.8075. Min Range: -1.8075

Max Act: 0.4536. Min Act: -0.0000

Data Index: 929022 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 1.8075. Min Range: -1.8075

Max Act: 0.4239. Min Act: -0.0000

Data Index: 974111 (C4 (Web Text))

Max Activating Token Index: 870