Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 906 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1457084 (Python Code)

Max Activating Token Index: 485

Text #1

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1138. Min Act: -0.0002

Data Index: 641717 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1163. Min Act: -0.0002

Data Index: 1422141 (Python Code)

Max Activating Token Index: 866

Text #3

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1055. Min Act: -0.0001

Data Index: 1389416 (Python Code)

Max Activating Token Index: 958

Text #4

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0995. Min Act: -0.0002

Data Index: 601614 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1073. Min Act: -0.0002

Data Index: 1457062 (Python Code)

Max Activating Token Index: 700

Text #6

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1608690 (Python Code)

Max Activating Token Index: 747

Text #7

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0953. Min Act: -0.0002

Data Index: 1611087 (Python Code)

Max Activating Token Index: 211

Text #8

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0958. Min Act: -0.0002

Data Index: 1378758 (Python Code)

Max Activating Token Index: 228

Text #9

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0976. Min Act: -0.0001

Data Index: 1570360 (Python Code)

Max Activating Token Index: 623

Text #10

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1008. Min Act: -0.0002

Data Index: 1476449 (Python Code)

Max Activating Token Index: 604

Text #11

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0984. Min Act: -0.0002

Data Index: 698695 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0944. Min Act: -0.0002

Data Index: 982845 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0943. Min Act: -0.0002

Data Index: 221250 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1615934 (Python Code)

Max Activating Token Index: 60

Text #15

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1460618 (Python Code)

Max Activating Token Index: 343

Text #16

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1437833 (Python Code)

Max Activating Token Index: 224

Text #17

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1391921 (Python Code)

Max Activating Token Index: 114

Text #18

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0841. Min Act: -0.0002

Data Index: 935513 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0912. Min Act: -0.0002

Data Index: 405177 (C4 (Web Text))

Max Activating Token Index: 718