Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1026 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.1058. Min Act: -0.0002

Data Index: 972084 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.1052. Min Act: -0.0002

Data Index: 106305 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.1022. Min Act: -0.0002

Data Index: 1247912 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0972. Min Act: -0.0002

Data Index: 1238148 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1020695 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0944. Min Act: -0.0002

Data Index: 50810 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0954. Min Act: -0.0002

Data Index: 967774 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0919. Min Act: -0.0002

Data Index: 24924 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0926. Min Act: -0.0001

Data Index: 1004588 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0863. Min Act: -0.0002

Data Index: 1319667 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0901. Min Act: -0.0002

Data Index: 101668 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0895. Min Act: -0.0002

Data Index: 1002073 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0906. Min Act: -0.0002

Data Index: 787719 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0919. Min Act: -0.0002

Data Index: 1076675 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1340074 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0837. Min Act: -0.0001

Data Index: 1183970 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0883. Min Act: -0.0002

Data Index: 637165 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0860. Min Act: -0.0001

Data Index: 870343 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0858. Min Act: -0.0002

Data Index: 990606 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0884. Min Act: -0.0002

Data Index: 117925 (C4 (Web Text))

Max Activating Token Index: 1014