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

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

Neuron 5253 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0763. Min Act: -0.0002

Data Index: 854774 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0819. Min Act: -0.0002

Data Index: 313821 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0658. Min Act: -0.0002

Data Index: 947923 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0590. Min Act: -0.0002

Data Index: 246410 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1052537 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0581. Min Act: -0.0002

Data Index: 620139 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0554. Min Act: -0.0002

Data Index: 614233 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1277540 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0539. Min Act: -0.0002

Data Index: 621095 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0554. Min Act: -0.0002

Data Index: 1117018 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0525. Min Act: -0.0002

Data Index: 370625 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0506. Min Act: -0.0002

Data Index: 679951 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1160380 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0507. Min Act: -0.0002

Data Index: 939417 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0505. Min Act: -0.0002

Data Index: 663062 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0491. Min Act: -0.0002

Data Index: 143879 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1278190 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1224881 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1221570 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.0819. Min Range: -0.0819

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1121277 (C4 (Web Text))

Max Activating Token Index: 208