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

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

Neuron 331 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8347. Min Range: -3.8347

Max Act: 3.8347. Min Act: -0.0000

Data Index: 1535196 (Python Code)

Max Activating Token Index: 907

Text #1

Max Range: 3.8347. Min Range: -3.8347

Max Act: 3.4938. Min Act: -0.0000

Data Index: 1497698 (Python Code)

Max Activating Token Index: 243

Text #2

Max Range: 3.8347. Min Range: -3.8347

Max Act: 3.3804. Min Act: -0.0000

Data Index: 651016 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 3.8347. Min Range: -3.8347

Max Act: 3.3237. Min Act: -0.0000

Data Index: 1509477 (Python Code)

Max Activating Token Index: 549

Text #4

Max Range: 3.8347. Min Range: -3.8347

Max Act: 3.3188. Min Act: -0.0000

Data Index: 1515145 (Python Code)

Max Activating Token Index: 217

Text #5

Max Range: 3.8347. Min Range: -3.8347

Max Act: 3.1506. Min Act: -0.0000

Data Index: 1379337 (Python Code)

Max Activating Token Index: 220

Text #6

Max Range: 3.8347. Min Range: -3.8347

Max Act: 3.1307. Min Act: -0.0000

Data Index: 1535571 (Python Code)

Max Activating Token Index: 898

Text #7

Max Range: 3.8347. Min Range: -3.8347

Max Act: 2.9598. Min Act: -0.0000

Data Index: 1557052 (Python Code)

Max Activating Token Index: 905

Text #8

Max Range: 3.8347. Min Range: -3.8347

Max Act: 3.2007. Min Act: -0.0000

Data Index: 1432570 (Python Code)

Max Activating Token Index: 29

Text #9

Max Range: 3.8347. Min Range: -3.8347

Max Act: 3.2084. Min Act: -0.0000

Data Index: 1608855 (Python Code)

Max Activating Token Index: 647

Text #10

Max Range: 3.8347. Min Range: -3.8347

Max Act: 3.1965. Min Act: -0.0000

Data Index: 1439058 (Python Code)

Max Activating Token Index: 117

Text #11

Max Range: 3.8347. Min Range: -3.8347

Max Act: 3.0544. Min Act: -0.0000

Data Index: 199953 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 3.8347. Min Range: -3.8347

Max Act: 3.3626. Min Act: -0.0000

Data Index: 747218 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 3.8347. Min Range: -3.8347

Max Act: 2.9588. Min Act: -0.0000

Data Index: 1187986 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 3.8347. Min Range: -3.8347

Max Act: 3.0479. Min Act: -0.0000

Data Index: 1612535 (Python Code)

Max Activating Token Index: 420

Text #15

Max Range: 3.8347. Min Range: -3.8347

Max Act: 3.0382. Min Act: -0.0000

Data Index: 614609 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 3.8347. Min Range: -3.8347

Max Act: 3.0706. Min Act: -0.0000

Data Index: 765856 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 3.8347. Min Range: -3.8347

Max Act: 3.0433. Min Act: -0.0000

Data Index: 5256 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 3.8347. Min Range: -3.8347

Max Act: 3.1571. Min Act: -0.0000

Data Index: 1579635 (Python Code)

Max Activating Token Index: 702

Text #19

Max Range: 3.8347. Min Range: -3.8347

Max Act: 2.8260. Min Act: -0.0000

Data Index: 1177063 (C4 (Web Text))

Max Activating Token Index: 189