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

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

Neuron 3870 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: 2.3947. Min Range: -2.3947

Max Act: 2.3947. Min Act: -0.0000

Data Index: 1448501 (Python Code)

Max Activating Token Index: 965

Text #1

Max Range: 2.3947. Min Range: -2.3947

Max Act: 2.3354. Min Act: -0.0000

Data Index: 1493612 (Python Code)

Max Activating Token Index: 794

Text #2

Max Range: 2.3947. Min Range: -2.3947

Max Act: 1.9806. Min Act: -0.0000

Data Index: 1417240 (Python Code)

Max Activating Token Index: 137

Text #3

Max Range: 2.3947. Min Range: -2.3947

Max Act: 2.0811. Min Act: -0.0000

Data Index: 1369537 (Python Code)

Max Activating Token Index: 232

Text #4

Max Range: 2.3947. Min Range: -2.3947

Max Act: 2.0287. Min Act: -0.0000

Data Index: 1412368 (Python Code)

Max Activating Token Index: 127

Text #5

Max Range: 2.3947. Min Range: -2.3947

Max Act: 1.7913. Min Act: -0.0000

Data Index: 1453333 (Python Code)

Max Activating Token Index: 293

Text #6

Max Range: 2.3947. Min Range: -2.3947

Max Act: 1.8758. Min Act: -0.0000

Data Index: 1374346 (Python Code)

Max Activating Token Index: 226

Text #7

Max Range: 2.3947. Min Range: -2.3947

Max Act: 1.9568. Min Act: -0.0000

Data Index: 1478132 (Python Code)

Max Activating Token Index: 87

Text #8

Max Range: 2.3947. Min Range: -2.3947

Max Act: 1.8211. Min Act: -0.0000

Data Index: 1432365 (Python Code)

Max Activating Token Index: 47

Text #9

Max Range: 2.3947. Min Range: -2.3947

Max Act: 1.7833. Min Act: -0.0000

Data Index: 1533279 (Python Code)

Max Activating Token Index: 110

Text #10

Max Range: 2.3947. Min Range: -2.3947

Max Act: 1.6393. Min Act: -0.0000

Data Index: 1558002 (Python Code)

Max Activating Token Index: 31

Text #11

Max Range: 2.3947. Min Range: -2.3947

Max Act: 1.8084. Min Act: -0.0000

Data Index: 1374847 (Python Code)

Max Activating Token Index: 241

Text #12

Max Range: 2.3947. Min Range: -2.3947

Max Act: 1.7033. Min Act: -0.0000

Data Index: 1495921 (Python Code)

Max Activating Token Index: 87

Text #13

Max Range: 2.3947. Min Range: -2.3947

Max Act: 1.6529. Min Act: -0.0000

Data Index: 1428153 (Python Code)

Max Activating Token Index: 85

Text #14

Max Range: 2.3947. Min Range: -2.3947

Max Act: 1.6425. Min Act: -0.0000

Data Index: 1632508 (Python Code)

Max Activating Token Index: 563

Text #15

Max Range: 2.3947. Min Range: -2.3947

Max Act: 1.6206. Min Act: -0.0000

Data Index: 1530474 (Python Code)

Max Activating Token Index: 437

Text #16

Max Range: 2.3947. Min Range: -2.3947

Max Act: 1.5177. Min Act: -0.0000

Data Index: 1382972 (Python Code)

Max Activating Token Index: 815

Text #17

Max Range: 2.3947. Min Range: -2.3947

Max Act: 1.5116. Min Act: -0.0000

Data Index: 1476481 (Python Code)

Max Activating Token Index: 28

Text #18

Max Range: 2.3947. Min Range: -2.3947

Max Act: 1.3850. Min Act: -0.0000

Data Index: 1649719 (Python Code)

Max Activating Token Index: 925

Text #19

Max Range: 2.3947. Min Range: -2.3947

Max Act: 1.5945. Min Act: -0.0000

Data Index: 1633040 (Python Code)

Max Activating Token Index: 393