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

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

Neuron 5030 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: 0.0487. Min Range: -0.0487

Max Act: 0.0487. Min Act: -0.0001

Data Index: 398634 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0466. Min Act: -0.0001

Data Index: 735706 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0468. Min Act: -0.0001

Data Index: 741226 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0451. Min Act: -0.0001

Data Index: 180459 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0450. Min Act: -0.0001

Data Index: 368332 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0443. Min Act: -0.0001

Data Index: 1518885 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0441. Min Act: -0.0001

Data Index: 1494445 (Python Code)

Max Activating Token Index: 139

Text #7

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0438. Min Act: -0.0001

Data Index: 252627 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0448. Min Act: -0.0001

Data Index: 1179055 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1445686 (Python Code)

Max Activating Token Index: 2

Text #10

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1575972 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1539835 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1436569 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0426. Min Act: -0.0001

Data Index: 1472955 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0427. Min Act: -0.0001

Data Index: 513268 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1439775 (Python Code)

Max Activating Token Index: 44

Text #16

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0426. Min Act: -0.0001

Data Index: 684229 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0430. Min Act: -0.0001

Data Index: 1263013 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0431. Min Act: -0.0001

Data Index: 895019 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0436. Min Act: -0.0001

Data Index: 676409 (C4 (Web Text))

Max Activating Token Index: 20