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

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

Neuron 3846 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1944. Min Range: -2.1944

Max Act: 2.1944. Min Act: -0.0000

Data Index: 1055541 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 2.1944. Min Range: -2.1944

Max Act: 2.0274. Min Act: -0.0000

Data Index: 1614841 (Python Code)

Max Activating Token Index: 182

Text #2

Max Range: 2.1944. Min Range: -2.1944

Max Act: 2.0079. Min Act: -0.0000

Data Index: 374588 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 2.1944. Min Range: -2.1944

Max Act: 2.0081. Min Act: -0.0000

Data Index: 754229 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.9817. Min Act: 0.0001

Data Index: 1238542 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.9517. Min Act: -0.0000

Data Index: 1264232 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.8814. Min Act: -0.0000

Data Index: 1126082 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.7573. Min Act: -0.0000

Data Index: 477253 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.6883. Min Act: -0.0000

Data Index: 425185 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.8863. Min Act: -0.0000

Data Index: 651633 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.6610. Min Act: -0.0000

Data Index: 1085351 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.7720. Min Act: -0.0000

Data Index: 915390 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.7473. Min Act: -0.0000

Data Index: 1552384 (Python Code)

Max Activating Token Index: 660

Text #13

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.7392. Min Act: -0.0000

Data Index: 1260125 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.7293. Min Act: -0.0000

Data Index: 602942 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.6093. Min Act: -0.0000

Data Index: 131028 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.7142. Min Act: -0.0000

Data Index: 1222747 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.6842. Min Act: -0.0000

Data Index: 1165811 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.6800. Min Act: -0.0000

Data Index: 1028429 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 2.1944. Min Range: -2.1944

Max Act: 1.6813. Min Act: -0.0000

Data Index: 1273815 (C4 (Web Text))

Max Activating Token Index: 25