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

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

Neuron 3000 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: 0.8577. Min Range: -0.8577

Max Act: 0.8577. Min Act: -0.0001

Data Index: 28325 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8486. Min Act: -0.0001

Data Index: 739597 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8513. Min Act: -0.0001

Data Index: 835624 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8487. Min Act: -0.0001

Data Index: 1251771 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8484. Min Act: -0.0001

Data Index: 462705 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8403. Min Act: -0.0001

Data Index: 113928 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8429. Min Act: -0.0001

Data Index: 589414 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8430. Min Act: -0.0001

Data Index: 379559 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8534. Min Act: -0.0001

Data Index: 452130 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8506. Min Act: -0.0001

Data Index: 961128 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8467. Min Act: -0.0001

Data Index: 929077 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8472. Min Act: -0.0001

Data Index: 544361 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8440. Min Act: -0.0001

Data Index: 965066 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8466. Min Act: -0.0001

Data Index: 315071 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8350. Min Act: -0.0001

Data Index: 987957 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8238. Min Act: -0.0001

Data Index: 697805 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8207. Min Act: -0.0001

Data Index: 59819 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8264. Min Act: -0.0001

Data Index: 614894 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8296. Min Act: -0.0001

Data Index: 272899 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.8577. Min Range: -0.8577

Max Act: 0.8073. Min Act: -0.0001

Data Index: 286238 (C4 (Web Text))

Max Activating Token Index: 58