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

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

Neuron 3421 in Layer 1

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: 0.4950. Min Range: -0.4950

Max Act: 0.4950. Min Act: -0.0002

Data Index: 997382 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4921. Min Act: -0.0002

Data Index: 516319 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4797. Min Act: -0.0002

Data Index: 228250 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4675. Min Act: -0.0002

Data Index: 515011 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4760. Min Act: -0.0002

Data Index: 698000 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4571. Min Act: -0.0002

Data Index: 77655 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4606. Min Act: -0.0002

Data Index: 1303236 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4655. Min Act: -0.0002

Data Index: 1138689 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4655. Min Act: -0.0002

Data Index: 988644 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4604. Min Act: -0.0002

Data Index: 246471 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4535. Min Act: -0.0002

Data Index: 837252 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4499. Min Act: -0.0002

Data Index: 1476655 (Python Code)

Max Activating Token Index: 491

Text #12

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4573. Min Act: -0.0002

Data Index: 394505 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4480. Min Act: -0.0002

Data Index: 1278339 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4382. Min Act: -0.0002

Data Index: 325340 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4386. Min Act: -0.0002

Data Index: 189782 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4461. Min Act: -0.0002

Data Index: 1377669 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4376. Min Act: -0.0002

Data Index: 1090472 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4386. Min Act: -0.0002

Data Index: 601942 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.4950. Min Range: -0.4950

Max Act: 0.4312. Min Act: -0.0002

Data Index: 231545 (C4 (Web Text))

Max Activating Token Index: 2