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

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

Neuron 4586 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: 4.3489. Min Range: -4.3489

Max Act: 4.3489. Min Act: -0.0000

Data Index: 1585521 (Python Code)

Max Activating Token Index: 581

Text #1

Max Range: 4.3489. Min Range: -4.3489

Max Act: 4.2748. Min Act: -0.0001

Data Index: 1562851 (Python Code)

Max Activating Token Index: 338

Text #2

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.9495. Min Act: -0.0001

Data Index: 1430867 (Python Code)

Max Activating Token Index: 792

Text #3

Max Range: 4.3489. Min Range: -4.3489

Max Act: 4.1551. Min Act: -0.0001

Data Index: 1398212 (Python Code)

Max Activating Token Index: 364

Text #4

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.8935. Min Act: -0.0001

Data Index: 1450979 (Python Code)

Max Activating Token Index: 11

Text #5

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.7026. Min Act: -0.0001

Data Index: 1369051 (Python Code)

Max Activating Token Index: 1020

Text #6

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.6919. Min Act: -0.0000

Data Index: 1447310 (Python Code)

Max Activating Token Index: 327

Text #7

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.8376. Min Act: -0.0001

Data Index: 1361125 (Python Code)

Max Activating Token Index: 103

Text #8

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.6597. Min Act: -0.0000

Data Index: 1479802 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.7542. Min Act: -0.0001

Data Index: 1561414 (Python Code)

Max Activating Token Index: 776

Text #10

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.5682. Min Act: -0.0000

Data Index: 1530870 (Python Code)

Max Activating Token Index: 890

Text #11

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.0634. Min Act: -0.0000

Data Index: 1415050 (Python Code)

Max Activating Token Index: 861

Text #12

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.6832. Min Act: -0.0000

Data Index: 1444512 (Python Code)

Max Activating Token Index: 991

Text #13

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.4276. Min Act: -0.0001

Data Index: 1479391 (Python Code)

Max Activating Token Index: 80

Text #14

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.3379. Min Act: -0.0000

Data Index: 1458008 (Python Code)

Max Activating Token Index: 601

Text #15

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.0916. Min Act: -0.0001

Data Index: 1564107 (Python Code)

Max Activating Token Index: 635

Text #16

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.1796. Min Act: -0.0000

Data Index: 1421556 (Python Code)

Max Activating Token Index: 388

Text #17

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.1737. Min Act: -0.0000

Data Index: 1366252 (Python Code)

Max Activating Token Index: 691

Text #18

Max Range: 4.3489. Min Range: -4.3489

Max Act: 2.9712. Min Act: -0.0001

Data Index: 1591475 (Python Code)

Max Activating Token Index: 823

Text #19

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.0479. Min Act: -0.0001

Data Index: 1556625 (Python Code)

Max Activating Token Index: 249