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

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

Neuron 4105 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: 2.8474. Min Range: -2.8474

Max Act: 2.8474. Min Act: -0.0000

Data Index: 853873 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 2.8474. Min Range: -2.8474

Max Act: 2.0392. Min Act: -0.0000

Data Index: 1329622 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 2.8474. Min Range: -2.8474

Max Act: 2.1077. Min Act: -0.0000

Data Index: 1325662 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 2.8474. Min Range: -2.8474

Max Act: 1.7755. Min Act: -0.0000

Data Index: 161913 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 2.8474. Min Range: -2.8474

Max Act: 1.5802. Min Act: -0.0000

Data Index: 1254523 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 2.8474. Min Range: -2.8474

Max Act: 1.5804. Min Act: -0.0000

Data Index: 1586882 (Python Code)

Max Activating Token Index: 163

Text #6

Max Range: 2.8474. Min Range: -2.8474

Max Act: 1.5466. Min Act: -0.0000

Data Index: 1035132 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 2.8474. Min Range: -2.8474

Max Act: 1.3793. Min Act: -0.0000

Data Index: 906273 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 2.8474. Min Range: -2.8474

Max Act: 1.5203. Min Act: -0.0000

Data Index: 1278635 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 2.8474. Min Range: -2.8474

Max Act: 1.5088. Min Act: -0.0000

Data Index: 1177721 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 2.8474. Min Range: -2.8474

Max Act: 1.1175. Min Act: -0.0000

Data Index: 463304 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 2.8474. Min Range: -2.8474

Max Act: 1.3610. Min Act: -0.0000

Data Index: 1596039 (Python Code)

Max Activating Token Index: 548

Text #12

Max Range: 2.8474. Min Range: -2.8474

Max Act: 1.3063. Min Act: -0.0000

Data Index: 956694 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 2.8474. Min Range: -2.8474

Max Act: 1.2937. Min Act: -0.0000

Data Index: 565265 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 2.8474. Min Range: -2.8474

Max Act: 1.2403. Min Act: -0.0000

Data Index: 1366721 (Python Code)

Max Activating Token Index: 666

Text #15

Max Range: 2.8474. Min Range: -2.8474

Max Act: 1.3374. Min Act: -0.0000

Data Index: 1505833 (Python Code)

Max Activating Token Index: 117

Text #16

Max Range: 2.8474. Min Range: -2.8474

Max Act: 1.3778. Min Act: -0.0000

Data Index: 1422895 (Python Code)

Max Activating Token Index: 673

Text #17

Max Range: 2.8474. Min Range: -2.8474

Max Act: 1.2523. Min Act: -0.0000

Data Index: 1547807 (Python Code)

Max Activating Token Index: 972

Text #18

Max Range: 2.8474. Min Range: -2.8474

Max Act: 1.3879. Min Act: -0.0000

Data Index: 1017148 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 2.8474. Min Range: -2.8474

Max Act: 1.3676. Min Act: -0.0000

Data Index: 985030 (C4 (Web Text))

Max Activating Token Index: 953