Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4034 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1311. Min Act: -0.0002

Data Index: 881461 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1201. Min Act: -0.0001

Data Index: 260461 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1154. Min Act: -0.0001

Data Index: 695051 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1174. Min Act: -0.0002

Data Index: 837835 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1081. Min Act: -0.0001

Data Index: 126500 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1125. Min Act: -0.0001

Data Index: 780771 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1067. Min Act: -0.0001

Data Index: 1343446 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1005. Min Act: -0.0001

Data Index: 1076071 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0970. Min Act: -0.0002

Data Index: 152218 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1066. Min Act: -0.0002

Data Index: 363712 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1026. Min Act: -0.0002

Data Index: 595827 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1040. Min Act: -0.0002

Data Index: 870403 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1056. Min Act: -0.0001

Data Index: 704568 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1026. Min Act: -0.0002

Data Index: 706694 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1029. Min Act: -0.0001

Data Index: 301614 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1029. Min Act: -0.0002

Data Index: 804459 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1033. Min Act: -0.0002

Data Index: 1345474 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1106. Min Act: -0.0002

Data Index: 528818 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1024. Min Act: -0.0002

Data Index: 864792 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0970. Min Act: -0.0002

Data Index: 761767 (C4 (Web Text))

Max Activating Token Index: 955