Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2831 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.3308. Min Act: -0.0001

Data Index: 1465646 (Python Code)

Max Activating Token Index: 463

Text #1

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.3288. Min Act: -0.0001

Data Index: 1591920 (Python Code)

Max Activating Token Index: 481

Text #2

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.2496. Min Act: -0.0001

Data Index: 1370065 (Python Code)

Max Activating Token Index: 930

Text #3

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.2710. Min Act: -0.0001

Data Index: 1560839 (Python Code)

Max Activating Token Index: 59

Text #4

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.4089. Min Act: -0.0001

Data Index: 1574063 (Python Code)

Max Activating Token Index: 186

Text #5

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.2287. Min Act: -0.0001

Data Index: 1501156 (Python Code)

Max Activating Token Index: 626

Text #6

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.2603. Min Act: -0.0001

Data Index: 1635521 (Python Code)

Max Activating Token Index: 322

Text #7

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.1907. Min Act: -0.0001

Data Index: 1603798 (Python Code)

Max Activating Token Index: 625

Text #8

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.2122. Min Act: -0.0001

Data Index: 1529974 (Python Code)

Max Activating Token Index: 311

Text #9

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.2492. Min Act: -0.0001

Data Index: 1408484 (Python Code)

Max Activating Token Index: 229

Text #10

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.2319. Min Act: -0.0001

Data Index: 1526176 (Python Code)

Max Activating Token Index: 440

Text #11

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.2136. Min Act: -0.0001

Data Index: 1503370 (Python Code)

Max Activating Token Index: 219

Text #12

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.1861. Min Act: -0.0001

Data Index: 1638649 (Python Code)

Max Activating Token Index: 87

Text #13

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.1569. Min Act: -0.0001

Data Index: 1479077 (Python Code)

Max Activating Token Index: 438

Text #14

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.1247. Min Act: -0.0001

Data Index: 1519049 (Python Code)

Max Activating Token Index: 527

Text #15

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.2180. Min Act: -0.0001

Data Index: 1584165 (Python Code)

Max Activating Token Index: 832

Text #16

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.2074. Min Act: -0.0001

Data Index: 1399703 (Python Code)

Max Activating Token Index: 33

Text #17

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.2145. Min Act: -0.0002

Data Index: 1375253 (Python Code)

Max Activating Token Index: 89

Text #18

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.1653. Min Act: -0.0001

Data Index: 1450489 (Python Code)

Max Activating Token Index: 188

Text #19

Max Range: 1.4089. Min Range: -1.4089

Max Act: 1.1977. Min Act: -0.0001

Data Index: 1442562 (Python Code)

Max Activating Token Index: 370