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

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

Neuron 1550 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.7971. Min Range: -3.7971

Max Act: 3.7971. Min Act: -0.0001

Data Index: 210718 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 3.7971. Min Range: -3.7971

Max Act: 3.1292. Min Act: -0.0000

Data Index: 107304 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 3.7971. Min Range: -3.7971

Max Act: 3.2493. Min Act: -0.0000

Data Index: 101062 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 3.7971. Min Range: -3.7971

Max Act: 3.0971. Min Act: -0.0000

Data Index: 1265995 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 3.7971. Min Range: -3.7971

Max Act: 3.1482. Min Act: -0.0001

Data Index: 693084 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 3.7971. Min Range: -3.7971

Max Act: 3.1052. Min Act: -0.0001

Data Index: 18292 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 3.7971. Min Range: -3.7971

Max Act: 2.8051. Min Act: -0.0001

Data Index: 1110723 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 3.7971. Min Range: -3.7971

Max Act: 3.1042. Min Act: -0.0000

Data Index: 748652 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 3.7971. Min Range: -3.7971

Max Act: 3.0725. Min Act: -0.0000

Data Index: 290595 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 3.7971. Min Range: -3.7971

Max Act: 3.2655. Min Act: -0.0001

Data Index: 1087466 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 3.7971. Min Range: -3.7971

Max Act: 2.8524. Min Act: -0.0000

Data Index: 680733 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 3.7971. Min Range: -3.7971

Max Act: 2.7573. Min Act: -0.0000

Data Index: 702017 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 3.7971. Min Range: -3.7971

Max Act: 2.9994. Min Act: -0.0000

Data Index: 1200654 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 3.7971. Min Range: -3.7971

Max Act: 2.5786. Min Act: -0.0001

Data Index: 343757 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 3.7971. Min Range: -3.7971

Max Act: 3.1009. Min Act: -0.0000

Data Index: 799221 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 3.7971. Min Range: -3.7971

Max Act: 2.1773. Min Act: -0.0000

Data Index: 281360 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 3.7971. Min Range: -3.7971

Max Act: 2.5963. Min Act: -0.0001

Data Index: 513156 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 3.7971. Min Range: -3.7971

Max Act: 2.7836. Min Act: -0.0001

Data Index: 1130022 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 3.7971. Min Range: -3.7971

Max Act: 2.9220. Min Act: -0.0000

Data Index: 480467 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 3.7971. Min Range: -3.7971

Max Act: 2.6071. Min Act: -0.0000

Data Index: 1235210 (C4 (Web Text))

Max Activating Token Index: 467