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

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

Neuron 375 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1194. Min Act: -0.0003

Data Index: 196394 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1109. Min Act: -0.0003

Data Index: 129871 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1104. Min Act: -0.0003

Data Index: 375613 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1098. Min Act: -0.0003

Data Index: 1215909 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0990. Min Act: -0.0003

Data Index: 1031376 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1041. Min Act: -0.0003

Data Index: 243627 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1005. Min Act: -0.0003

Data Index: 995987 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0976. Min Act: -0.0003

Data Index: 331837 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0958. Min Act: -0.0003

Data Index: 167452 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0969. Min Act: -0.0003

Data Index: 1350735 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0967. Min Act: -0.0003

Data Index: 213008 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0891. Min Act: -0.0003

Data Index: 1055719 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0944. Min Act: -0.0003

Data Index: 407808 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0821. Min Act: -0.0003

Data Index: 1157288 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0966. Min Act: -0.0003

Data Index: 1086567 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0909. Min Act: -0.0003

Data Index: 213409 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0890. Min Act: -0.0003

Data Index: 684046 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0925. Min Act: -0.0003

Data Index: 17710 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0902. Min Act: -0.0003

Data Index: 676087 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0930. Min Act: -0.0003

Data Index: 102540 (C4 (Web Text))

Max Activating Token Index: 24