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

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

Neuron 1132 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.2827. Min Range: -2.2827

Max Act: 2.2827. Min Act: -0.0002

Data Index: 917038 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 2.2827. Min Range: -2.2827

Max Act: 1.9405. Min Act: -0.0002

Data Index: 603089 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 2.2827. Min Range: -2.2827

Max Act: 1.9224. Min Act: -0.0002

Data Index: 521588 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 2.2827. Min Range: -2.2827

Max Act: 1.9216. Min Act: -0.0002

Data Index: 939847 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 2.2827. Min Range: -2.2827

Max Act: 1.9179. Min Act: -0.0002

Data Index: 63722 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 2.2827. Min Range: -2.2827

Max Act: 1.9050. Min Act: -0.0002

Data Index: 869846 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 2.2827. Min Range: -2.2827

Max Act: 1.8493. Min Act: -0.0002

Data Index: 485602 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 2.2827. Min Range: -2.2827

Max Act: 1.9361. Min Act: -0.0002

Data Index: 273723 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 2.2827. Min Range: -2.2827

Max Act: 1.8351. Min Act: -0.0002

Data Index: 172233 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 2.2827. Min Range: -2.2827

Max Act: 1.8643. Min Act: -0.0002

Data Index: 222925 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 2.2827. Min Range: -2.2827

Max Act: 1.8791. Min Act: -0.0002

Data Index: 870754 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 2.2827. Min Range: -2.2827

Max Act: 1.8751. Min Act: -0.0002

Data Index: 642033 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 2.2827. Min Range: -2.2827

Max Act: 1.8598. Min Act: -0.0002

Data Index: 608744 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 2.2827. Min Range: -2.2827

Max Act: 1.8718. Min Act: -0.0002

Data Index: 795714 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 2.2827. Min Range: -2.2827

Max Act: 1.8867. Min Act: -0.0002

Data Index: 98564 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 2.2827. Min Range: -2.2827

Max Act: 1.8871. Min Act: -0.0002

Data Index: 548889 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 2.2827. Min Range: -2.2827

Max Act: 1.8700. Min Act: -0.0002

Data Index: 1133075 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 2.2827. Min Range: -2.2827

Max Act: 1.8081. Min Act: -0.0002

Data Index: 615538 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 2.2827. Min Range: -2.2827

Max Act: 1.8529. Min Act: -0.0002

Data Index: 478749 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 2.2827. Min Range: -2.2827

Max Act: 1.8475. Min Act: -0.0002

Data Index: 1090838 (C4 (Web Text))

Max Activating Token Index: 82