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

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

Neuron 3951 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0104. Min Range: -1.0104

Max Act: 1.0104. Min Act: -0.0001

Data Index: 1631511 (Python Code)

Max Activating Token Index: 934

Text #1

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.8894. Min Act: -0.0001

Data Index: 1435016 (Python Code)

Max Activating Token Index: 1021

Text #2

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.7813. Min Act: -0.0001

Data Index: 1535352 (Python Code)

Max Activating Token Index: 859

Text #3

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.7820. Min Act: -0.0001

Data Index: 1608125 (Python Code)

Max Activating Token Index: 397

Text #4

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.7173. Min Act: -0.0001

Data Index: 1575719 (Python Code)

Max Activating Token Index: 636

Text #5

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.7414. Min Act: -0.0001

Data Index: 1556267 (Python Code)

Max Activating Token Index: 197

Text #6

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.6416. Min Act: -0.0001

Data Index: 1591617 (Python Code)

Max Activating Token Index: 772

Text #7

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.6531. Min Act: -0.0001

Data Index: 1571881 (Python Code)

Max Activating Token Index: 720

Text #8

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.7410. Min Act: -0.0001

Data Index: 1423155 (Python Code)

Max Activating Token Index: 852

Text #9

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.6389. Min Act: -0.0001

Data Index: 1379426 (Python Code)

Max Activating Token Index: 943

Text #10

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.6069. Min Act: -0.0001

Data Index: 1609368 (Python Code)

Max Activating Token Index: 579

Text #11

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.6719. Min Act: -0.0001

Data Index: 1477046 (Python Code)

Max Activating Token Index: 646

Text #12

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.6027. Min Act: -0.0001

Data Index: 1401079 (Python Code)

Max Activating Token Index: 603

Text #13

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.5965. Min Act: -0.0001

Data Index: 1435770 (Python Code)

Max Activating Token Index: 647

Text #14

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.6057. Min Act: -0.0001

Data Index: 1400286 (Python Code)

Max Activating Token Index: 837

Text #15

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.5050. Min Act: -0.0001

Data Index: 1494932 (Python Code)

Max Activating Token Index: 781

Text #16

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.5864. Min Act: -0.0001

Data Index: 1647458 (Python Code)

Max Activating Token Index: 6

Text #17

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.6005. Min Act: -0.0001

Data Index: 1495711 (Python Code)

Max Activating Token Index: 662

Text #18

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.5819. Min Act: -0.0001

Data Index: 1491185 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.5165. Min Act: -0.0001

Data Index: 1411364 (Python Code)

Max Activating Token Index: 963