Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2536 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.8391. Min Act: -0.0001

Data Index: 791651 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.6223. Min Act: -0.0001

Data Index: 913911 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.6211. Min Act: -0.0001

Data Index: 1097566 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.6049. Min Act: -0.0001

Data Index: 1103625 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.6907. Min Act: -0.0001

Data Index: 1082777 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.5693. Min Act: -0.0001

Data Index: 64469 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.4630. Min Act: -0.0001

Data Index: 999400 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.4830. Min Act: -0.0001

Data Index: 1120488 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.4904. Min Act: -0.0001

Data Index: 1114995 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.4514. Min Act: -0.0001

Data Index: 743435 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.4016. Min Act: -0.0001

Data Index: 908927 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.4512. Min Act: -0.0001

Data Index: 1148319 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.4734. Min Act: -0.0001

Data Index: 1041693 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.4509. Min Act: -0.0001

Data Index: 289380 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.4034. Min Act: -0.0001

Data Index: 419391 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.4412. Min Act: -0.0001

Data Index: 1012035 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.4349. Min Act: -0.0001

Data Index: 143684 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.3951. Min Act: -0.0001

Data Index: 1150701 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.2547. Min Act: -0.0001

Data Index: 950773 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.1194. Min Act: -0.0001

Data Index: 1035170 (C4 (Web Text))

Max Activating Token Index: 648