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

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

Neuron 78 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4698. Min Range: -3.4698

Max Act: 3.4698. Min Act: -0.0002

Data Index: 1643779 (Python Code)

Max Activating Token Index: 706

Text #1

Max Range: 3.4698. Min Range: -3.4698

Max Act: 1.9613. Min Act: -0.0002

Data Index: 611447 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 3.4698. Min Range: -3.4698

Max Act: 1.6206. Min Act: -0.0002

Data Index: 1111099 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 3.4698. Min Range: -3.4698

Max Act: 1.5680. Min Act: -0.0002

Data Index: 34057 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 3.4698. Min Range: -3.4698

Max Act: 1.5120. Min Act: -0.0002

Data Index: 1173306 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 3.4698. Min Range: -3.4698

Max Act: 1.3952. Min Act: -0.0002

Data Index: 1601652 (Python Code)

Max Activating Token Index: 103

Text #6

Max Range: 3.4698. Min Range: -3.4698

Max Act: 1.2109. Min Act: -0.0002

Data Index: 1479881 (Python Code)

Max Activating Token Index: 172

Text #7

Max Range: 3.4698. Min Range: -3.4698

Max Act: 1.1682. Min Act: -0.0002

Data Index: 1044588 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 3.4698. Min Range: -3.4698

Max Act: 1.1377. Min Act: -0.0002

Data Index: 73637 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 3.4698. Min Range: -3.4698

Max Act: 1.0325. Min Act: -0.0002

Data Index: 784054 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 3.4698. Min Range: -3.4698

Max Act: 1.0134. Min Act: -0.0002

Data Index: 87020 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 3.4698. Min Range: -3.4698

Max Act: 0.9954. Min Act: -0.0002

Data Index: 1594968 (Python Code)

Max Activating Token Index: 593

Text #12

Max Range: 3.4698. Min Range: -3.4698

Max Act: 1.0161. Min Act: -0.0002

Data Index: 118289 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 3.4698. Min Range: -3.4698

Max Act: 1.0212. Min Act: -0.0002

Data Index: 1438075 (Python Code)

Max Activating Token Index: 66

Text #14

Max Range: 3.4698. Min Range: -3.4698

Max Act: 0.9096. Min Act: -0.0002

Data Index: 1360562 (Python Code)

Max Activating Token Index: 597

Text #15

Max Range: 3.4698. Min Range: -3.4698

Max Act: 0.8180. Min Act: -0.0002

Data Index: 935352 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 3.4698. Min Range: -3.4698

Max Act: 0.8613. Min Act: -0.0002

Data Index: 1483328 (Python Code)

Max Activating Token Index: 816

Text #17

Max Range: 3.4698. Min Range: -3.4698

Max Act: 0.8379. Min Act: -0.0002

Data Index: 1377033 (Python Code)

Max Activating Token Index: 943

Text #18

Max Range: 3.4698. Min Range: -3.4698

Max Act: 0.8234. Min Act: -0.0002

Data Index: 1238902 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 3.4698. Min Range: -3.4698

Max Act: 0.8085. Min Act: -0.0002

Data Index: 169061 (C4 (Web Text))

Max Activating Token Index: 965