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

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

Neuron 5534 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1976. Min Act: -0.0001

Data Index: 1038613 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1603. Min Act: -0.0001

Data Index: 1332371 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1402. Min Act: -0.0001

Data Index: 608106 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1378. Min Act: -0.0001

Data Index: 713761 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.0935. Min Act: -0.0001

Data Index: 874750 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.0988. Min Act: -0.0001

Data Index: 802746 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.0952. Min Act: -0.0001

Data Index: 165310 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.0695. Min Act: -0.0001

Data Index: 1262057 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.0849. Min Act: -0.0001

Data Index: 399922 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.0754. Min Act: -0.0001

Data Index: 1025651 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.0755. Min Act: -0.0001

Data Index: 676402 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1163672 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1127653 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.0663. Min Act: -0.0001

Data Index: 125298 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1089022 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.0738. Min Act: -0.0001

Data Index: 165551 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.0670. Min Act: -0.0001

Data Index: 71809 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1019692 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.0681. Min Act: -0.0001

Data Index: 471166 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.0710. Min Act: -0.0001

Data Index: 187116 (C4 (Web Text))

Max Activating Token Index: 351