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

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

Neuron 3261 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: 2.3994. Min Range: -2.3994

Max Act: 2.0287. Min Act: -0.0000

Data Index: 1616298 (Python Code)

Max Activating Token Index: 104

Text #1

Max Range: 2.3994. Min Range: -2.3994

Max Act: 2.3994. Min Act: -0.0000

Data Index: 1310796 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 2.3994. Min Range: -2.3994

Max Act: 2.3814. Min Act: -0.0000

Data Index: 1509958 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 2.3994. Min Range: -2.3994

Max Act: 2.1940. Min Act: -0.0000

Data Index: 1524150 (Python Code)

Max Activating Token Index: 121

Text #4

Max Range: 2.3994. Min Range: -2.3994

Max Act: 2.0067. Min Act: -0.0000

Data Index: 242317 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 2.3994. Min Range: -2.3994

Max Act: 2.1165. Min Act: -0.0000

Data Index: 372578 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 2.3994. Min Range: -2.3994

Max Act: 1.9971. Min Act: -0.0000

Data Index: 1044391 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 2.3994. Min Range: -2.3994

Max Act: 2.0153. Min Act: -0.0000

Data Index: 1204900 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 2.3994. Min Range: -2.3994

Max Act: 1.8579. Min Act: -0.0000

Data Index: 786277 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 2.3994. Min Range: -2.3994

Max Act: 1.8082. Min Act: -0.0000

Data Index: 1205647 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 2.3994. Min Range: -2.3994

Max Act: 2.0115. Min Act: -0.0000

Data Index: 574826 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 2.3994. Min Range: -2.3994

Max Act: 1.8800. Min Act: -0.0000

Data Index: 674771 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 2.3994. Min Range: -2.3994

Max Act: 1.8651. Min Act: -0.0000

Data Index: 147170 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 2.3994. Min Range: -2.3994

Max Act: 1.8375. Min Act: -0.0000

Data Index: 453215 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 2.3994. Min Range: -2.3994

Max Act: 1.8095. Min Act: -0.0000

Data Index: 1568210 (Python Code)

Max Activating Token Index: 108

Text #15

Max Range: 2.3994. Min Range: -2.3994

Max Act: 1.8640. Min Act: -0.0000

Data Index: 911747 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 2.3994. Min Range: -2.3994

Max Act: 1.7512. Min Act: -0.0000

Data Index: 187813 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 2.3994. Min Range: -2.3994

Max Act: 1.7281. Min Act: -0.0000

Data Index: 827113 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 2.3994. Min Range: -2.3994

Max Act: 1.6498. Min Act: -0.0000

Data Index: 389369 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 2.3994. Min Range: -2.3994

Max Act: 1.7068. Min Act: -0.0000

Data Index: 1369834 (Python Code)

Max Activating Token Index: 367