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

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

Neuron 1029 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: 0.0464. Min Range: -0.0464

Max Act: 0.0461. Min Act: -0.0002

Data Index: 831897 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0464. Min Act: -0.0002

Data Index: 834594 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0444. Min Act: -0.0002

Data Index: 130290 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0452. Min Act: -0.0002

Data Index: 75633 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0440. Min Act: -0.0002

Data Index: 201272 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1462229 (Python Code)

Max Activating Token Index: 455

Text #6

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0440. Min Act: -0.0002

Data Index: 899195 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1165330 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0434. Min Act: -0.0002

Data Index: 567455 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1340458 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0428. Min Act: -0.0002

Data Index: 41836 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0431. Min Act: -0.0002

Data Index: 194516 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1399483 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0434. Min Act: -0.0002

Data Index: 989418 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0430. Min Act: -0.0002

Data Index: 928781 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0423. Min Act: -0.0002

Data Index: 642389 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0418. Min Act: -0.0002

Data Index: 311553 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1336594 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0418. Min Act: -0.0002

Data Index: 627165 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1108869 (C4 (Web Text))

Max Activating Token Index: 745