Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 405 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.4906. Min Act: -0.0000

Data Index: 1572065 (Python Code)

Max Activating Token Index: 24

Text #1

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.4300. Min Act: -0.0000

Data Index: 1395129 (Python Code)

Max Activating Token Index: 115

Text #2

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.4110. Min Act: -0.0000

Data Index: 1430681 (Python Code)

Max Activating Token Index: 897

Text #3

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.3956. Min Act: -0.0000

Data Index: 1585585 (Python Code)

Max Activating Token Index: 713

Text #4

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.3786. Min Act: -0.0000

Data Index: 1613437 (Python Code)

Max Activating Token Index: 33

Text #5

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.3216. Min Act: -0.0000

Data Index: 1506266 (Python Code)

Max Activating Token Index: 471

Text #6

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.3149. Min Act: -0.0000

Data Index: 1552196 (Python Code)

Max Activating Token Index: 98

Text #7

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.2897. Min Act: -0.0000

Data Index: 1378398 (Python Code)

Max Activating Token Index: 282

Text #8

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.2001. Min Act: -0.0000

Data Index: 1475019 (Python Code)

Max Activating Token Index: 160

Text #9

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.2336. Min Act: -0.0000

Data Index: 1378707 (Python Code)

Max Activating Token Index: 761

Text #10

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.3263. Min Act: -0.0000

Data Index: 1547507 (Python Code)

Max Activating Token Index: 912

Text #11

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.2428. Min Act: -0.0000

Data Index: 1535881 (Python Code)

Max Activating Token Index: 125

Text #12

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.2268. Min Act: -0.0000

Data Index: 1544563 (Python Code)

Max Activating Token Index: 11

Text #13

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.1492. Min Act: -0.0000

Data Index: 1427947 (Python Code)

Max Activating Token Index: 57

Text #14

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.1848. Min Act: -0.0000

Data Index: 1546660 (Python Code)

Max Activating Token Index: 107

Text #15

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.1761. Min Act: -0.0000

Data Index: 1458524 (Python Code)

Max Activating Token Index: 383

Text #16

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.2056. Min Act: -0.0000

Data Index: 1581007 (Python Code)

Max Activating Token Index: 357

Text #17

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.2125. Min Act: -0.0000

Data Index: 1619520 (Python Code)

Max Activating Token Index: 330

Text #18

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1367919 (Python Code)

Max Activating Token Index: 332

Text #19

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.1389. Min Act: -0.0000

Data Index: 1427949 (Python Code)

Max Activating Token Index: 725