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

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

Neuron 347 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.9209. Min Act: -0.0001

Data Index: 292880 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8813. Min Act: -0.0001

Data Index: 1357356 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8529. Min Act: -0.0001

Data Index: 934792 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8037. Min Act: -0.0001

Data Index: 807637 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8330. Min Act: -0.0001

Data Index: 1033972 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8404. Min Act: -0.0000

Data Index: 1330372 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8226. Min Act: -0.0001

Data Index: 1613958 (Python Code)

Max Activating Token Index: 899

Text #7

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8057. Min Act: -0.0001

Data Index: 1597571 (Python Code)

Max Activating Token Index: 865

Text #8

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7606. Min Act: -0.0000

Data Index: 652175 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7474. Min Act: -0.0001

Data Index: 1110945 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8454. Min Act: -0.0000

Data Index: 10465 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7596. Min Act: -0.0000

Data Index: 922890 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7800. Min Act: -0.0001

Data Index: 1187848 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7792. Min Act: -0.0001

Data Index: 1541989 (Python Code)

Max Activating Token Index: 612

Text #14

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8552. Min Act: -0.0001

Data Index: 478687 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7819. Min Act: -0.0000

Data Index: 1103957 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7521. Min Act: -0.0001

Data Index: 182047 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7514. Min Act: -0.0001

Data Index: 532835 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7956. Min Act: -0.0001

Data Index: 1125487 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7430. Min Act: -0.0001

Data Index: 436099 (C4 (Web Text))

Max Activating Token Index: 907