Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 884 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0427. Min Act: -0.0006

Data Index: 1526163 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0410. Min Act: -0.0005

Data Index: 1625014 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0380. Min Act: -0.0005

Data Index: 1649294 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0391. Min Act: -0.0006

Data Index: 1616989 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0381. Min Act: -0.0005

Data Index: 1615927 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0382. Min Act: -0.0005

Data Index: 1625749 (Python Code)

Max Activating Token Index: 4

Text #6

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0376. Min Act: -0.0005

Data Index: 1643032 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0368. Min Act: -0.0005

Data Index: 1643587 (Python Code)

Max Activating Token Index: 2

Text #8

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0364. Min Act: -0.0005

Data Index: 1577151 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0368. Min Act: -0.0005

Data Index: 1422647 (Python Code)

Max Activating Token Index: 9

Text #10

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0355. Min Act: -0.0005

Data Index: 1642422 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0354. Min Act: -0.0005

Data Index: 1588932 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0360. Min Act: -0.0005

Data Index: 1418045 (Python Code)

Max Activating Token Index: 7

Text #13

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0351. Min Act: -0.0005

Data Index: 1639348 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0350. Min Act: -0.0005

Data Index: 1648890 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0347. Min Act: -0.0005

Data Index: 1452013 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0347. Min Act: -0.0005

Data Index: 1593142 (Python Code)

Max Activating Token Index: 3

Text #17

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0345. Min Act: -0.0005

Data Index: 1459693 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0337. Min Act: -0.0005

Data Index: 1423619 (Python Code)

Max Activating Token Index: 3

Text #19

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0338. Min Act: -0.0005

Data Index: 1542132 (Python Code)

Max Activating Token Index: 5