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

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

Neuron 2669 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.7234. Min Act: -0.0000

Data Index: 1419893 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1499188 (Python Code)

Max Activating Token Index: 365

Text #2

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1603610 (Python Code)

Max Activating Token Index: 391

Text #3

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1437640 (Python Code)

Max Activating Token Index: 474

Text #4

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4485. Min Act: -0.0000

Data Index: 1592536 (Python Code)

Max Activating Token Index: 607

Text #5

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4643. Min Act: -0.0000

Data Index: 1489556 (Python Code)

Max Activating Token Index: 149

Text #6

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4558. Min Act: -0.0000

Data Index: 1440870 (Python Code)

Max Activating Token Index: 180

Text #7

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1540588 (Python Code)

Max Activating Token Index: 898

Text #8

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4522. Min Act: -0.0000

Data Index: 1453267 (Python Code)

Max Activating Token Index: 167

Text #9

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1592092 (Python Code)

Max Activating Token Index: 449

Text #10

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1407547 (Python Code)

Max Activating Token Index: 43

Text #11

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4280. Min Act: -0.0000

Data Index: 1434806 (Python Code)

Max Activating Token Index: 598

Text #12

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1539890 (Python Code)

Max Activating Token Index: 254

Text #13

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1512701 (Python Code)

Max Activating Token Index: 864

Text #14

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1608116 (Python Code)

Max Activating Token Index: 163

Text #15

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1402107 (Python Code)

Max Activating Token Index: 663

Text #16

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4049. Min Act: -0.0000

Data Index: 1532088 (Python Code)

Max Activating Token Index: 1018

Text #17

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4288. Min Act: -0.0000

Data Index: 1607929 (Python Code)

Max Activating Token Index: 71

Text #18

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1498948 (Python Code)

Max Activating Token Index: 299

Text #19

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1396489 (Python Code)

Max Activating Token Index: 73