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

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

Neuron 3888 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9543. Min Range: -1.9543

Max Act: 1.9543. Min Act: -0.0000

Data Index: 373895 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 1.9543. Min Range: -1.9543

Max Act: 1.2195. Min Act: -0.0000

Data Index: 204776 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 1.9543. Min Range: -1.9543

Max Act: 1.1418. Min Act: -0.0000

Data Index: 549094 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 1.9543. Min Range: -1.9543

Max Act: 0.9784. Min Act: -0.0000

Data Index: 604073 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 1.9543. Min Range: -1.9543

Max Act: 0.8404. Min Act: -0.0000

Data Index: 391463 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 1.9543. Min Range: -1.9543

Max Act: 0.8769. Min Act: -0.0000

Data Index: 699860 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 1.9543. Min Range: -1.9543

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1076904 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 1.9543. Min Range: -1.9543

Max Act: 0.7838. Min Act: -0.0000

Data Index: 428124 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 1.9543. Min Range: -1.9543

Max Act: 0.7049. Min Act: -0.0000

Data Index: 384962 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 1.9543. Min Range: -1.9543

Max Act: 0.6925. Min Act: -0.0000

Data Index: 369219 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 1.9543. Min Range: -1.9543

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1144480 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 1.9543. Min Range: -1.9543

Max Act: 0.7206. Min Act: -0.0000

Data Index: 1247188 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 1.9543. Min Range: -1.9543

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1030289 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 1.9543. Min Range: -1.9543

Max Act: 0.6789. Min Act: -0.0000

Data Index: 847029 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 1.9543. Min Range: -1.9543

Max Act: 0.6849. Min Act: -0.0000

Data Index: 368953 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 1.9543. Min Range: -1.9543

Max Act: 0.6637. Min Act: -0.0000

Data Index: 261278 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 1.9543. Min Range: -1.9543

Max Act: 0.6176. Min Act: -0.0000

Data Index: 705558 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 1.9543. Min Range: -1.9543

Max Act: 0.5900. Min Act: -0.0000

Data Index: 892204 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 1.9543. Min Range: -1.9543

Max Act: 0.5988. Min Act: -0.0000

Data Index: 499427 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 1.9543. Min Range: -1.9543

Max Act: 0.6145. Min Act: -0.0000

Data Index: 615731 (C4 (Web Text))

Max Activating Token Index: 207