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

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

Neuron 5902 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3821. Min Range: -2.3821

Max Act: 2.3821. Min Act: -0.0000

Data Index: 1276810 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 2.3821. Min Range: -2.3821

Max Act: 2.3383. Min Act: -0.0000

Data Index: 878472 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 2.3821. Min Range: -2.3821

Max Act: 2.3411. Min Act: -0.0000

Data Index: 303251 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 2.3821. Min Range: -2.3821

Max Act: 1.8978. Min Act: -0.0000

Data Index: 813571 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 2.3821. Min Range: -2.3821

Max Act: 1.8786. Min Act: -0.0000

Data Index: 766683 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 2.3821. Min Range: -2.3821

Max Act: 2.1623. Min Act: -0.0000

Data Index: 816453 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 2.3821. Min Range: -2.3821

Max Act: 2.0215. Min Act: -0.0000

Data Index: 460729 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 2.3821. Min Range: -2.3821

Max Act: 1.9980. Min Act: -0.0000

Data Index: 19228 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 2.3821. Min Range: -2.3821

Max Act: 1.9919. Min Act: -0.0000

Data Index: 131589 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 2.3821. Min Range: -2.3821

Max Act: 2.0996. Min Act: -0.0000

Data Index: 461957 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 2.3821. Min Range: -2.3821

Max Act: 1.6481. Min Act: -0.0000

Data Index: 291229 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 2.3821. Min Range: -2.3821

Max Act: 1.8407. Min Act: -0.0000

Data Index: 877734 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 2.3821. Min Range: -2.3821

Max Act: 1.8278. Min Act: -0.0000

Data Index: 172369 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 2.3821. Min Range: -2.3821

Max Act: 1.8309. Min Act: -0.0000

Data Index: 891122 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 2.3821. Min Range: -2.3821

Max Act: 1.8003. Min Act: -0.0000

Data Index: 378882 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 2.3821. Min Range: -2.3821

Max Act: 1.6584. Min Act: -0.0000

Data Index: 399664 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 2.3821. Min Range: -2.3821

Max Act: 1.7379. Min Act: -0.0000

Data Index: 212481 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 2.3821. Min Range: -2.3821

Max Act: 1.7195. Min Act: -0.0000

Data Index: 628379 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 2.3821. Min Range: -2.3821

Max Act: 1.7304. Min Act: -0.0000

Data Index: 1207653 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 2.3821. Min Range: -2.3821

Max Act: 1.7066. Min Act: -0.0000

Data Index: 424270 (C4 (Web Text))

Max Activating Token Index: 509