Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1133 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.1022. Min Act: -0.0001

Data Index: 201447 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.1010. Min Act: -0.0001

Data Index: 163825 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.1046. Min Act: -0.0001

Data Index: 357982 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1132988 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0987. Min Act: -0.0001

Data Index: 1331446 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0995. Min Act: -0.0001

Data Index: 908724 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.1023. Min Act: -0.0001

Data Index: 323099 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0947. Min Act: -0.0001

Data Index: 203742 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0977. Min Act: -0.0001

Data Index: 200673 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0941. Min Act: -0.0001

Data Index: 1278050 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0971. Min Act: -0.0001

Data Index: 620686 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0966. Min Act: -0.0001

Data Index: 216858 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.1002. Min Act: -0.0001

Data Index: 262103 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0939. Min Act: -0.0001

Data Index: 458649 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0968. Min Act: -0.0001

Data Index: 1230066 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0954. Min Act: -0.0001

Data Index: 866930 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0956. Min Act: -0.0001

Data Index: 8522 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0952. Min Act: -0.0001

Data Index: 186354 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0881. Min Act: -0.0001

Data Index: 924859 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0941. Min Act: -0.0001

Data Index: 1160543 (C4 (Web Text))

Max Activating Token Index: 362