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

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

Neuron 5616 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: 0.0474. Min Range: -0.0474

Max Act: 0.0474. Min Act: -0.0001

Data Index: 1199589 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1425710 (Python Code)

Max Activating Token Index: 726

Text #2

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0461. Min Act: -0.0001

Data Index: 1615906 (Python Code)

Max Activating Token Index: 51

Text #3

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0453. Min Act: -0.0001

Data Index: 1533794 (Python Code)

Max Activating Token Index: 836

Text #4

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0448. Min Act: -0.0001

Data Index: 1284811 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0450. Min Act: -0.0001

Data Index: 1422475 (Python Code)

Max Activating Token Index: 239

Text #6

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1057920 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0432. Min Act: -0.0001

Data Index: 1370253 (Python Code)

Max Activating Token Index: 314

Text #8

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0421. Min Act: -0.0001

Data Index: 945936 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0423. Min Act: -0.0001

Data Index: 22238 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1603697 (Python Code)

Max Activating Token Index: 393

Text #11

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0423. Min Act: -0.0001

Data Index: 676460 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1048696 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0422. Min Act: -0.0001

Data Index: 1489783 (Python Code)

Max Activating Token Index: 605

Text #14

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0426. Min Act: -0.0001

Data Index: 167065 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0413. Min Act: -0.0001

Data Index: 1137300 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1235191 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0418. Min Act: -0.0001

Data Index: 394440 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0412. Min Act: -0.0001

Data Index: 678047 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0418. Min Act: -0.0001

Data Index: 1463160 (Python Code)

Max Activating Token Index: 699