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

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

Neuron 4984 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: 0.2543. Min Range: -0.2543

Max Act: 0.2543. Min Act: -0.0002

Data Index: 1323242 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2522. Min Act: -0.0002

Data Index: 1339171 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2439. Min Act: -0.0002

Data Index: 673934 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2287. Min Act: -0.0002

Data Index: 640600 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2170. Min Act: -0.0003

Data Index: 1195022 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2171. Min Act: -0.0002

Data Index: 195165 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2147. Min Act: -0.0003

Data Index: 1162798 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2116. Min Act: -0.0002

Data Index: 601277 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2141. Min Act: -0.0002

Data Index: 1101687 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2041. Min Act: -0.0002

Data Index: 1539149 (Python Code)

Max Activating Token Index: 36

Text #10

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2025. Min Act: -0.0002

Data Index: 1145738 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2086. Min Act: -0.0002

Data Index: 1560838 (Python Code)

Max Activating Token Index: 29

Text #12

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2020. Min Act: -0.0002

Data Index: 510257 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2033. Min Act: -0.0002

Data Index: 1042699 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2081. Min Act: -0.0002

Data Index: 1259147 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2036. Min Act: -0.0002

Data Index: 118567 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2050. Min Act: -0.0002

Data Index: 255298 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1996. Min Act: -0.0002

Data Index: 1489986 (Python Code)

Max Activating Token Index: 794

Text #18

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.2018. Min Act: -0.0002

Data Index: 1504547 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 0.2543. Min Range: -0.2543

Max Act: 0.1993. Min Act: -0.0002

Data Index: 1027662 (C4 (Web Text))

Max Activating Token Index: 653