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

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

Neuron 652 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.8333. Min Act: -0.0000

Data Index: 1609211 (Python Code)

Max Activating Token Index: 104

Text #1

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.9075. Min Act: -0.0000

Data Index: 101627 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.5761. Min Act: -0.0000

Data Index: 1079456 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.7789. Min Act: -0.0000

Data Index: 489263 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.6038. Min Act: -0.0000

Data Index: 1108961 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.5702. Min Act: -0.0000

Data Index: 874728 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.4113. Min Act: -0.0000

Data Index: 1038898 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.5312. Min Act: -0.0000

Data Index: 1279126 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.3912. Min Act: -0.0000

Data Index: 1550821 (Python Code)

Max Activating Token Index: 251

Text #9

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.2652. Min Act: -0.0000

Data Index: 29201 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.1968. Min Act: -0.0000

Data Index: 505843 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.2870. Min Act: -0.0000

Data Index: 1067082 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.1525. Min Act: -0.0000

Data Index: 191207 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.3256. Min Act: -0.0000

Data Index: 208743 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.1051. Min Act: -0.0000

Data Index: 1310795 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.3153. Min Act: -0.0000

Data Index: 635169 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.3307. Min Act: -0.0000

Data Index: 167540 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.1918. Min Act: -0.0000

Data Index: 839396 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.1846. Min Act: -0.0000

Data Index: 7020 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 2.9075. Min Range: -2.9075

Max Act: 2.0534. Min Act: -0.0000

Data Index: 1044636 (C4 (Web Text))

Max Activating Token Index: 823