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

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

Neuron 4907 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1015. Min Range: -5.1015

Max Act: 5.1015. Min Act: -0.0000

Data Index: 114561 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 5.1015. Min Range: -5.1015

Max Act: 4.5535. Min Act: -0.0000

Data Index: 942949 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 5.1015. Min Range: -5.1015

Max Act: 4.1123. Min Act: -0.0000

Data Index: 125436 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 5.1015. Min Range: -5.1015

Max Act: 4.0166. Min Act: -0.0000

Data Index: 671519 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 5.1015. Min Range: -5.1015

Max Act: 3.7810. Min Act: -0.0000

Data Index: 890501 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 5.1015. Min Range: -5.1015

Max Act: 3.3119. Min Act: -0.0000

Data Index: 1204587 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 5.1015. Min Range: -5.1015

Max Act: 3.0350. Min Act: -0.0000

Data Index: 703034 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 5.1015. Min Range: -5.1015

Max Act: 3.1479. Min Act: -0.0000

Data Index: 928131 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 5.1015. Min Range: -5.1015

Max Act: 3.1146. Min Act: -0.0000

Data Index: 365183 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 5.1015. Min Range: -5.1015

Max Act: 3.1378. Min Act: -0.0000

Data Index: 200399 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 5.1015. Min Range: -5.1015

Max Act: 3.0970. Min Act: -0.0000

Data Index: 828921 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 5.1015. Min Range: -5.1015

Max Act: 3.0117. Min Act: -0.0000

Data Index: 726484 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 5.1015. Min Range: -5.1015

Max Act: 2.9950. Min Act: -0.0000

Data Index: 732468 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 5.1015. Min Range: -5.1015

Max Act: 2.8164. Min Act: -0.0000

Data Index: 544649 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 5.1015. Min Range: -5.1015

Max Act: 2.7367. Min Act: -0.0000

Data Index: 225379 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 5.1015. Min Range: -5.1015

Max Act: 2.8800. Min Act: -0.0000

Data Index: 704081 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 5.1015. Min Range: -5.1015

Max Act: 2.8633. Min Act: -0.0000

Data Index: 538945 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 5.1015. Min Range: -5.1015

Max Act: 2.6987. Min Act: -0.0000

Data Index: 420846 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 5.1015. Min Range: -5.1015

Max Act: 2.6765. Min Act: -0.0000

Data Index: 1009659 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 5.1015. Min Range: -5.1015

Max Act: 2.6830. Min Act: -0.0000

Data Index: 262188 (C4 (Web Text))

Max Activating Token Index: 780