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

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

Neuron 4939 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.5333. Min Act: -0.0000

Data Index: 1637662 (Python Code)

Max Activating Token Index: 838

Text #1

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.5244. Min Act: -0.0000

Data Index: 1646825 (Python Code)

Max Activating Token Index: 683

Text #2

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.2599. Min Act: -0.0000

Data Index: 1647027 (Python Code)

Max Activating Token Index: 807

Text #3

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.4123. Min Act: -0.0000

Data Index: 1583478 (Python Code)

Max Activating Token Index: 371

Text #4

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.3319. Min Act: -0.0000

Data Index: 1631946 (Python Code)

Max Activating Token Index: 1015

Text #5

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.3109. Min Act: -0.0000

Data Index: 1410221 (Python Code)

Max Activating Token Index: 877

Text #6

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.3683. Min Act: -0.0000

Data Index: 1415610 (Python Code)

Max Activating Token Index: 991

Text #7

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.3412. Min Act: -0.0000

Data Index: 1473942 (Python Code)

Max Activating Token Index: 421

Text #8

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.3110. Min Act: -0.0000

Data Index: 1438437 (Python Code)

Max Activating Token Index: 124

Text #9

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.1694. Min Act: -0.0000

Data Index: 1592747 (Python Code)

Max Activating Token Index: 134

Text #10

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.0331. Min Act: -0.0000

Data Index: 1415392 (Python Code)

Max Activating Token Index: 245

Text #11

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.1645. Min Act: -0.0000

Data Index: 1603092 (Python Code)

Max Activating Token Index: 113

Text #12

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.0810. Min Act: -0.0000

Data Index: 1483259 (Python Code)

Max Activating Token Index: 219

Text #13

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.1692. Min Act: -0.0000

Data Index: 1446377 (Python Code)

Max Activating Token Index: 232

Text #14

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.1609. Min Act: -0.0000

Data Index: 1481260 (Python Code)

Max Activating Token Index: 251

Text #15

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.1102. Min Act: -0.0000

Data Index: 1477353 (Python Code)

Max Activating Token Index: 154

Text #16

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.1165. Min Act: -0.0000

Data Index: 1386909 (Python Code)

Max Activating Token Index: 211

Text #17

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.1310. Min Act: -0.0000

Data Index: 1362647 (Python Code)

Max Activating Token Index: 33

Text #18

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.1339. Min Act: -0.0000

Data Index: 1362176 (Python Code)

Max Activating Token Index: 157

Text #19

Max Range: 1.5333. Min Range: -1.5333

Max Act: 1.0961. Min Act: -0.0000

Data Index: 1394070 (Python Code)

Max Activating Token Index: 258