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

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

Neuron 3573 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3983. Min Range: -2.3983

Max Act: 2.3983. Min Act: -0.0000

Data Index: 292230 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 2.3983. Min Range: -2.3983

Max Act: 1.8957. Min Act: -0.0000

Data Index: 651041 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 2.3983. Min Range: -2.3983

Max Act: 1.7917. Min Act: -0.0000

Data Index: 521757 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 2.3983. Min Range: -2.3983

Max Act: 1.8162. Min Act: -0.0000

Data Index: 393149 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 2.3983. Min Range: -2.3983

Max Act: 1.8270. Min Act: -0.0000

Data Index: 709930 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 2.3983. Min Range: -2.3983

Max Act: 1.9233. Min Act: -0.0000

Data Index: 772956 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 2.3983. Min Range: -2.3983

Max Act: 1.6971. Min Act: -0.0000

Data Index: 808819 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 2.3983. Min Range: -2.3983

Max Act: 1.9144. Min Act: -0.0000

Data Index: 477967 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 2.3983. Min Range: -2.3983

Max Act: 1.7836. Min Act: -0.0000

Data Index: 276304 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 2.3983. Min Range: -2.3983

Max Act: 1.6702. Min Act: -0.0000

Data Index: 940462 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 2.3983. Min Range: -2.3983

Max Act: 1.8057. Min Act: -0.0000

Data Index: 152162 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 2.3983. Min Range: -2.3983

Max Act: 1.6606. Min Act: -0.0000

Data Index: 1176323 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 2.3983. Min Range: -2.3983

Max Act: 1.7914. Min Act: -0.0000

Data Index: 718421 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 2.3983. Min Range: -2.3983

Max Act: 1.6650. Min Act: -0.0000

Data Index: 1237386 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 2.3983. Min Range: -2.3983

Max Act: 1.5667. Min Act: -0.0000

Data Index: 678162 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 2.3983. Min Range: -2.3983

Max Act: 1.6657. Min Act: -0.0000

Data Index: 834338 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 2.3983. Min Range: -2.3983

Max Act: 1.6605. Min Act: -0.0000

Data Index: 971346 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 2.3983. Min Range: -2.3983

Max Act: 1.6679. Min Act: -0.0000

Data Index: 1320063 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 2.3983. Min Range: -2.3983

Max Act: 1.6476. Min Act: -0.0000

Data Index: 1066747 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 2.3983. Min Range: -2.3983

Max Act: 1.7022. Min Act: -0.0000

Data Index: 86763 (C4 (Web Text))

Max Activating Token Index: 497