Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1892 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1537155 (Python Code)

Max Activating Token Index: 246

Text #1

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.8036. Min Act: -0.0000

Data Index: 118448 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1318146 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6891. Min Act: -0.0000

Data Index: 801287 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6457. Min Act: -0.0000

Data Index: 396902 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6521. Min Act: -0.0000

Data Index: 863948 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.7150. Min Act: -0.0000

Data Index: 1423185 (Python Code)

Max Activating Token Index: 971

Text #7

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.7098. Min Act: -0.0000

Data Index: 1614754 (Python Code)

Max Activating Token Index: 204

Text #8

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1488646 (Python Code)

Max Activating Token Index: 386

Text #9

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6154. Min Act: -0.0000

Data Index: 205727 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5918. Min Act: -0.0000

Data Index: 27587 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6108. Min Act: -0.0000

Data Index: 929709 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6107. Min Act: -0.0000

Data Index: 711592 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1028057 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5476. Min Act: -0.0000

Data Index: 993869 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5628. Min Act: -0.0000

Data Index: 900858 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1627063 (Python Code)

Max Activating Token Index: 650

Text #17

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1543438 (Python Code)

Max Activating Token Index: 802

Text #18

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5855. Min Act: -0.0000

Data Index: 507538 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5603. Min Act: -0.0000

Data Index: 861955 (C4 (Web Text))

Max Activating Token Index: 586