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

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

Neuron 1536 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: 1.2165. Min Range: -1.2165

Max Act: 1.2165. Min Act: -0.0000

Data Index: 1373513 (Python Code)

Max Activating Token Index: 126

Text #1

Max Range: 1.2165. Min Range: -1.2165

Max Act: 1.1146. Min Act: -0.0000

Data Index: 1649126 (Python Code)

Max Activating Token Index: 480

Text #2

Max Range: 1.2165. Min Range: -1.2165

Max Act: 1.0988. Min Act: -0.0000

Data Index: 1402474 (Python Code)

Max Activating Token Index: 119

Text #3

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.9313. Min Act: -0.0000

Data Index: 1400670 (Python Code)

Max Activating Token Index: 148

Text #4

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.9176. Min Act: -0.0000

Data Index: 1360104 (Python Code)

Max Activating Token Index: 119

Text #5

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1457030 (Python Code)

Max Activating Token Index: 1019

Text #6

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1468330 (Python Code)

Max Activating Token Index: 1017

Text #7

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1435033 (Python Code)

Max Activating Token Index: 1017

Text #8

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1435146 (Python Code)

Max Activating Token Index: 125

Text #9

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1510065 (Python Code)

Max Activating Token Index: 399

Text #10

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.9047. Min Act: -0.0000

Data Index: 1455947 (Python Code)

Max Activating Token Index: 294

Text #11

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1422108 (Python Code)

Max Activating Token Index: 94

Text #12

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1593961 (Python Code)

Max Activating Token Index: 629

Text #13

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8454. Min Act: -0.0000

Data Index: 1576200 (Python Code)

Max Activating Token Index: 940

Text #14

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1522356 (Python Code)

Max Activating Token Index: 542

Text #15

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8354. Min Act: -0.0000

Data Index: 1593017 (Python Code)

Max Activating Token Index: 755

Text #16

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8340. Min Act: -0.0000

Data Index: 1552671 (Python Code)

Max Activating Token Index: 493

Text #17

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8589. Min Act: -0.0000

Data Index: 1594599 (Python Code)

Max Activating Token Index: 882

Text #18

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8389. Min Act: -0.0000

Data Index: 1436204 (Python Code)

Max Activating Token Index: 349

Text #19

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.7389. Min Act: -0.0000

Data Index: 1385700 (Python Code)

Max Activating Token Index: 816