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

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

Neuron 5044 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: 1.5060. Min Range: -1.5060

Max Act: 1.3622. Min Act: -0.0000

Data Index: 1387198 (Python Code)

Max Activating Token Index: 90

Text #1

Max Range: 1.5060. Min Range: -1.5060

Max Act: 1.3408. Min Act: -0.0000

Data Index: 88937 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 1.5060. Min Range: -1.5060

Max Act: 1.3035. Min Act: -0.0000

Data Index: 466198 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 1.5060. Min Range: -1.5060

Max Act: 1.3144. Min Act: -0.0000

Data Index: 496670 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 1.5060. Min Range: -1.5060

Max Act: 1.5060. Min Act: -0.0000

Data Index: 1383103 (Python Code)

Max Activating Token Index: 709

Text #5

Max Range: 1.5060. Min Range: -1.5060

Max Act: 1.1612. Min Act: -0.0000

Data Index: 1433198 (Python Code)

Max Activating Token Index: 698

Text #6

Max Range: 1.5060. Min Range: -1.5060

Max Act: 1.3142. Min Act: -0.0000

Data Index: 734059 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 1.5060. Min Range: -1.5060

Max Act: 1.2505. Min Act: -0.0000

Data Index: 941467 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 1.5060. Min Range: -1.5060

Max Act: 1.2896. Min Act: -0.0000

Data Index: 1413965 (Python Code)

Max Activating Token Index: 70

Text #9

Max Range: 1.5060. Min Range: -1.5060

Max Act: 1.2778. Min Act: -0.0000

Data Index: 180087 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 1.5060. Min Range: -1.5060

Max Act: 1.4862. Min Act: -0.0000

Data Index: 1448046 (Python Code)

Max Activating Token Index: 457

Text #11

Max Range: 1.5060. Min Range: -1.5060

Max Act: 1.1345. Min Act: -0.0000

Data Index: 1644867 (Python Code)

Max Activating Token Index: 695

Text #12

Max Range: 1.5060. Min Range: -1.5060

Max Act: 1.2930. Min Act: -0.0000

Data Index: 702837 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 1.5060. Min Range: -1.5060

Max Act: 1.1096. Min Act: -0.0000

Data Index: 1040433 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 1.5060. Min Range: -1.5060

Max Act: 1.1452. Min Act: -0.0000

Data Index: 249321 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 1.5060. Min Range: -1.5060

Max Act: 1.1105. Min Act: -0.0000

Data Index: 1443539 (Python Code)

Max Activating Token Index: 290

Text #16

Max Range: 1.5060. Min Range: -1.5060

Max Act: 1.1258. Min Act: -0.0000

Data Index: 1128648 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 1.5060. Min Range: -1.5060

Max Act: 1.1351. Min Act: -0.0000

Data Index: 717757 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 1.5060. Min Range: -1.5060

Max Act: 1.1750. Min Act: -0.0000

Data Index: 1606402 (Python Code)

Max Activating Token Index: 286

Text #19

Max Range: 1.5060. Min Range: -1.5060

Max Act: 1.1500. Min Act: -0.0000

Data Index: 1027530 (C4 (Web Text))

Max Activating Token Index: 599