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

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

Neuron 6020 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0405. Min Act: -0.0001

Data Index: 717067 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0402. Min Act: -0.0001

Data Index: 792220 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0402. Min Act: -0.0001

Data Index: 128903 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0403. Min Act: -0.0001

Data Index: 839171 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0395. Min Act: -0.0001

Data Index: 965045 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0387. Min Act: -0.0001

Data Index: 314756 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0393. Min Act: -0.0001

Data Index: 130735 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0386. Min Act: -0.0001

Data Index: 165032 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0390. Min Act: -0.0001

Data Index: 1145375 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0396. Min Act: -0.0001

Data Index: 973986 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0390. Min Act: -0.0002

Data Index: 165982 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0390. Min Act: -0.0001

Data Index: 20020 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0385. Min Act: -0.0001

Data Index: 327693 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0384. Min Act: -0.0001

Data Index: 615509 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0396. Min Act: -0.0001

Data Index: 483766 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0384. Min Act: -0.0001

Data Index: 502436 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0384. Min Act: -0.0001

Data Index: 1132400 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0390. Min Act: -0.0001

Data Index: 1017902 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0391. Min Act: -0.0001

Data Index: 506807 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0386. Min Act: -0.0001

Data Index: 1293796 (C4 (Web Text))

Max Activating Token Index: 765