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

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

Neuron 1514 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6869. Min Range: -5.6869

Max Act: 5.6869. Min Act: -0.0000

Data Index: 1262594 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 5.6869. Min Range: -5.6869

Max Act: 5.3273. Min Act: -0.0000

Data Index: 1137275 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 5.6869. Min Range: -5.6869

Max Act: 5.2088. Min Act: -0.0000

Data Index: 681435 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 5.6869. Min Range: -5.6869

Max Act: 4.9790. Min Act: -0.0000

Data Index: 1277945 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 5.6869. Min Range: -5.6869

Max Act: 4.9812. Min Act: -0.0000

Data Index: 1348017 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 5.6869. Min Range: -5.6869

Max Act: 4.9109. Min Act: -0.0000

Data Index: 831758 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 5.6869. Min Range: -5.6869

Max Act: 4.8811. Min Act: -0.0000

Data Index: 223313 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 5.6869. Min Range: -5.6869

Max Act: 4.9093. Min Act: -0.0000

Data Index: 429084 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 5.6869. Min Range: -5.6869

Max Act: 4.8430. Min Act: -0.0000

Data Index: 586439 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 5.6869. Min Range: -5.6869

Max Act: 4.7712. Min Act: -0.0000

Data Index: 605325 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 5.6869. Min Range: -5.6869

Max Act: 4.7516. Min Act: -0.0000

Data Index: 957244 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 5.6869. Min Range: -5.6869

Max Act: 4.4241. Min Act: -0.0000

Data Index: 322693 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 5.6869. Min Range: -5.6869

Max Act: 4.1451. Min Act: -0.0000

Data Index: 42827 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 5.6869. Min Range: -5.6869

Max Act: 4.3299. Min Act: -0.0000

Data Index: 718184 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 5.6869. Min Range: -5.6869

Max Act: 4.4555. Min Act: -0.0000

Data Index: 713181 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 5.6869. Min Range: -5.6869

Max Act: 4.4314. Min Act: -0.0000

Data Index: 120985 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 5.6869. Min Range: -5.6869

Max Act: 4.2148. Min Act: -0.0000

Data Index: 174821 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 5.6869. Min Range: -5.6869

Max Act: 4.1055. Min Act: -0.0000

Data Index: 1148874 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 5.6869. Min Range: -5.6869

Max Act: 4.1221. Min Act: -0.0000

Data Index: 760149 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 5.6869. Min Range: -5.6869

Max Act: 4.0777. Min Act: -0.0000

Data Index: 984523 (C4 (Web Text))

Max Activating Token Index: 238