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

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

Neuron 5806 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1563. Min Range: -4.1563

Max Act: 4.1563. Min Act: -0.0000

Data Index: 1039731 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 4.1563. Min Range: -4.1563

Max Act: 3.9190. Min Act: -0.0000

Data Index: 723325 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 4.1563. Min Range: -4.1563

Max Act: 3.8841. Min Act: -0.0000

Data Index: 975095 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 4.1563. Min Range: -4.1563

Max Act: 3.7012. Min Act: -0.0000

Data Index: 242788 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 4.1563. Min Range: -4.1563

Max Act: 3.4154. Min Act: -0.0000

Data Index: 211118 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 4.1563. Min Range: -4.1563

Max Act: 3.5493. Min Act: -0.0000

Data Index: 679499 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 4.1563. Min Range: -4.1563

Max Act: 3.7326. Min Act: -0.0000

Data Index: 638930 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 4.1563. Min Range: -4.1563

Max Act: 3.3582. Min Act: -0.0000

Data Index: 153842 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 4.1563. Min Range: -4.1563

Max Act: 3.4820. Min Act: -0.0000

Data Index: 432023 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 4.1563. Min Range: -4.1563

Max Act: 3.4146. Min Act: -0.0000

Data Index: 591679 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 4.1563. Min Range: -4.1563

Max Act: 3.4248. Min Act: -0.0000

Data Index: 1109549 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 4.1563. Min Range: -4.1563

Max Act: 3.3713. Min Act: -0.0000

Data Index: 45692 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 4.1563. Min Range: -4.1563

Max Act: 3.4939. Min Act: -0.0000

Data Index: 658368 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 4.1563. Min Range: -4.1563

Max Act: 3.3394. Min Act: -0.0000

Data Index: 755228 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 4.1563. Min Range: -4.1563

Max Act: 3.4770. Min Act: -0.0000

Data Index: 1156615 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 4.1563. Min Range: -4.1563

Max Act: 3.1663. Min Act: -0.0000

Data Index: 1271501 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 4.1563. Min Range: -4.1563

Max Act: 3.4764. Min Act: -0.0000

Data Index: 975467 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 4.1563. Min Range: -4.1563

Max Act: 3.4629. Min Act: -0.0000

Data Index: 1088327 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 4.1563. Min Range: -4.1563

Max Act: 3.2713. Min Act: -0.0000

Data Index: 726607 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 4.1563. Min Range: -4.1563

Max Act: 3.2691. Min Act: -0.0000

Data Index: 343138 (C4 (Web Text))

Max Activating Token Index: 22