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

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

Neuron 4323 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: 2.4860. Min Range: -2.4860

Max Act: 2.4860. Min Act: -0.0000

Data Index: 1567513 (Python Code)

Max Activating Token Index: 88

Text #1

Max Range: 2.4860. Min Range: -2.4860

Max Act: 2.2196. Min Act: -0.0000

Data Index: 1542100 (Python Code)

Max Activating Token Index: 321

Text #2

Max Range: 2.4860. Min Range: -2.4860

Max Act: 2.0901. Min Act: -0.0000

Data Index: 1566927 (Python Code)

Max Activating Token Index: 927

Text #3

Max Range: 2.4860. Min Range: -2.4860

Max Act: 2.1041. Min Act: -0.0000

Data Index: 1631745 (Python Code)

Max Activating Token Index: 506

Text #4

Max Range: 2.4860. Min Range: -2.4860

Max Act: 2.1428. Min Act: -0.0000

Data Index: 1655635 (Python Code)

Max Activating Token Index: 153

Text #5

Max Range: 2.4860. Min Range: -2.4860

Max Act: 2.0144. Min Act: -0.0000

Data Index: 1547253 (Python Code)

Max Activating Token Index: 920

Text #6

Max Range: 2.4860. Min Range: -2.4860

Max Act: 2.0687. Min Act: -0.0000

Data Index: 1556732 (Python Code)

Max Activating Token Index: 501

Text #7

Max Range: 2.4860. Min Range: -2.4860

Max Act: 1.7228. Min Act: -0.0000

Data Index: 1470717 (Python Code)

Max Activating Token Index: 216

Text #8

Max Range: 2.4860. Min Range: -2.4860

Max Act: 1.7465. Min Act: -0.0000

Data Index: 1437257 (Python Code)

Max Activating Token Index: 874

Text #9

Max Range: 2.4860. Min Range: -2.4860

Max Act: 1.7313. Min Act: -0.0000

Data Index: 1514338 (Python Code)

Max Activating Token Index: 872

Text #10

Max Range: 2.4860. Min Range: -2.4860

Max Act: 1.9365. Min Act: -0.0000

Data Index: 1527770 (Python Code)

Max Activating Token Index: 461

Text #11

Max Range: 2.4860. Min Range: -2.4860

Max Act: 1.7834. Min Act: -0.0000

Data Index: 1361496 (Python Code)

Max Activating Token Index: 132

Text #12

Max Range: 2.4860. Min Range: -2.4860

Max Act: 1.6774. Min Act: -0.0000

Data Index: 1649415 (Python Code)

Max Activating Token Index: 567

Text #13

Max Range: 2.4860. Min Range: -2.4860

Max Act: 1.7560. Min Act: -0.0000

Data Index: 1403377 (Python Code)

Max Activating Token Index: 311

Text #14

Max Range: 2.4860. Min Range: -2.4860

Max Act: 1.6525. Min Act: -0.0000

Data Index: 1497045 (Python Code)

Max Activating Token Index: 136

Text #15

Max Range: 2.4860. Min Range: -2.4860

Max Act: 1.7979. Min Act: -0.0000

Data Index: 1519883 (Python Code)

Max Activating Token Index: 971

Text #16

Max Range: 2.4860. Min Range: -2.4860

Max Act: 1.9092. Min Act: -0.0000

Data Index: 1380517 (Python Code)

Max Activating Token Index: 979

Text #17

Max Range: 2.4860. Min Range: -2.4860

Max Act: 1.7247. Min Act: -0.0000

Data Index: 1457633 (Python Code)

Max Activating Token Index: 514

Text #18

Max Range: 2.4860. Min Range: -2.4860

Max Act: 1.6768. Min Act: -0.0000

Data Index: 1400555 (Python Code)

Max Activating Token Index: 214

Text #19

Max Range: 2.4860. Min Range: -2.4860

Max Act: 1.7330. Min Act: -0.0000

Data Index: 1498239 (Python Code)

Max Activating Token Index: 914