Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2381 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.6649. Min Act: -0.0001

Data Index: 1364484 (Python Code)

Max Activating Token Index: 280

Text #1

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.6399. Min Act: -0.0001

Data Index: 1437178 (Python Code)

Max Activating Token Index: 441

Text #2

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.6497. Min Act: -0.0001

Data Index: 1468686 (Python Code)

Max Activating Token Index: 487

Text #3

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.6090. Min Act: -0.0001

Data Index: 1569635 (Python Code)

Max Activating Token Index: 768

Text #4

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.6114. Min Act: -0.0001

Data Index: 1579786 (Python Code)

Max Activating Token Index: 582

Text #5

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5761. Min Act: -0.0001

Data Index: 1566553 (Python Code)

Max Activating Token Index: 898

Text #6

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.6061. Min Act: -0.0001

Data Index: 1430137 (Python Code)

Max Activating Token Index: 665

Text #7

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.6402. Min Act: -0.0001

Data Index: 1542645 (Python Code)

Max Activating Token Index: 847

Text #8

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.6154. Min Act: -0.0001

Data Index: 1391771 (Python Code)

Max Activating Token Index: 229

Text #9

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5662. Min Act: -0.0001

Data Index: 1591383 (Python Code)

Max Activating Token Index: 855

Text #10

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5892. Min Act: -0.0001

Data Index: 1654321 (Python Code)

Max Activating Token Index: 372

Text #11

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5854. Min Act: -0.0001

Data Index: 1375047 (Python Code)

Max Activating Token Index: 403

Text #12

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5636. Min Act: -0.0001

Data Index: 1418740 (Python Code)

Max Activating Token Index: 404

Text #13

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5566. Min Act: -0.0001

Data Index: 1475820 (Python Code)

Max Activating Token Index: 474

Text #14

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.6037. Min Act: -0.0001

Data Index: 1362516 (Python Code)

Max Activating Token Index: 684

Text #15

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5435. Min Act: -0.0001

Data Index: 1589627 (Python Code)

Max Activating Token Index: 895

Text #16

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5263. Min Act: -0.0001

Data Index: 1560045 (Python Code)

Max Activating Token Index: 959

Text #17

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5195. Min Act: -0.0001

Data Index: 1437396 (Python Code)

Max Activating Token Index: 393

Text #18

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5866. Min Act: -0.0001

Data Index: 1454273 (Python Code)

Max Activating Token Index: 871

Text #19

Max Range: 0.6649. Min Range: -0.6649

Max Act: 0.5461. Min Act: -0.0001

Data Index: 1388349 (Python Code)

Max Activating Token Index: 640