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

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

Neuron 996 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: 0.2608. Min Range: -0.2608

Max Act: 0.2608. Min Act: -0.0001

Data Index: 750393 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2542. Min Act: -0.0001

Data Index: 900483 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2442. Min Act: -0.0001

Data Index: 1040095 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2457. Min Act: -0.0001

Data Index: 540431 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2400. Min Act: -0.0001

Data Index: 1307635 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2463. Min Act: -0.0001

Data Index: 777052 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2423. Min Act: -0.0001

Data Index: 466581 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2403. Min Act: -0.0001

Data Index: 1185379 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2390. Min Act: -0.0001

Data Index: 585736 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2377. Min Act: -0.0001

Data Index: 561462 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2437. Min Act: -0.0001

Data Index: 599967 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2361. Min Act: -0.0001

Data Index: 146166 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2363. Min Act: -0.0001

Data Index: 771229 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2378. Min Act: -0.0001

Data Index: 95542 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2395. Min Act: -0.0001

Data Index: 949869 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2365. Min Act: -0.0001

Data Index: 753314 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2354. Min Act: -0.0001

Data Index: 664288 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2371. Min Act: -0.0001

Data Index: 450400 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2335. Min Act: -0.0001

Data Index: 1298251 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2285. Min Act: -0.0001

Data Index: 559648 (C4 (Web Text))

Max Activating Token Index: 18