Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5094 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1296. Min Act: -0.0000

Data Index: 615184 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1047. Min Act: -0.0000

Data Index: 332950 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1004. Min Act: -0.0001

Data Index: 725289 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1185988 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1039. Min Act: -0.0000

Data Index: 950931 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0974. Min Act: -0.0000

Data Index: 609116 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1011. Min Act: -0.0000

Data Index: 1077396 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0880. Min Act: -0.0000

Data Index: 1059338 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0942. Min Act: -0.0000

Data Index: 35043 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0925. Min Act: -0.0000

Data Index: 882389 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0907. Min Act: -0.0000

Data Index: 120193 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0896. Min Act: -0.0000

Data Index: 528167 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0893. Min Act: -0.0000

Data Index: 225033 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0914. Min Act: -0.0000

Data Index: 784172 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1336591 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0915. Min Act: -0.0000

Data Index: 630663 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0803. Min Act: -0.0000

Data Index: 488189 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0778. Min Act: -0.0001

Data Index: 279353 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0831. Min Act: -0.0000

Data Index: 746756 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.0822. Min Act: -0.0000

Data Index: 448104 (C4 (Web Text))

Max Activating Token Index: 861