Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2438 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0576. Min Act: -0.0004

Data Index: 1495597 (Python Code)

Max Activating Token Index: 790

Text #1

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0430. Min Act: -0.0004

Data Index: 1421489 (Python Code)

Max Activating Token Index: 461

Text #2

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0414. Min Act: -0.0004

Data Index: 1643747 (Python Code)

Max Activating Token Index: 64

Text #3

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0383. Min Act: -0.0004

Data Index: 1484763 (Python Code)

Max Activating Token Index: 216

Text #4

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0383. Min Act: -0.0004

Data Index: 1567759 (Python Code)

Max Activating Token Index: 239

Text #5

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0395. Min Act: -0.0004

Data Index: 1424694 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0365. Min Act: -0.0004

Data Index: 1617875 (Python Code)

Max Activating Token Index: 791

Text #7

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0394. Min Act: -0.0004

Data Index: 1402039 (Python Code)

Max Activating Token Index: 948

Text #8

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0361. Min Act: -0.0004

Data Index: 1466339 (Python Code)

Max Activating Token Index: 104

Text #9

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0369. Min Act: -0.0004

Data Index: 1417384 (Python Code)

Max Activating Token Index: 880

Text #10

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0378. Min Act: -0.0004

Data Index: 1466826 (Python Code)

Max Activating Token Index: 222

Text #11

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0357. Min Act: -0.0004

Data Index: 1418233 (Python Code)

Max Activating Token Index: 190

Text #12

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0351. Min Act: -0.0004

Data Index: 1618130 (Python Code)

Max Activating Token Index: 304

Text #13

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0356. Min Act: -0.0004

Data Index: 1528699 (Python Code)

Max Activating Token Index: 502

Text #14

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0361. Min Act: -0.0004

Data Index: 1576278 (Python Code)

Max Activating Token Index: 453

Text #15

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0360. Min Act: -0.0004

Data Index: 1588115 (Python Code)

Max Activating Token Index: 687

Text #16

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0354. Min Act: -0.0004

Data Index: 1432583 (Python Code)

Max Activating Token Index: 55

Text #17

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0362. Min Act: -0.0004

Data Index: 1378976 (Python Code)

Max Activating Token Index: 877

Text #18

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0344. Min Act: -0.0004

Data Index: 1409818 (Python Code)

Max Activating Token Index: 17

Text #19

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0344. Min Act: -0.0004

Data Index: 1374599 (Python Code)

Max Activating Token Index: 69