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

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

Neuron 4771 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: 0.0558. Min Range: -0.0558

Max Act: 0.0558. Min Act: -0.0001

Data Index: 1333469 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0543. Min Act: -0.0001

Data Index: 190315 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0532. Min Act: -0.0001

Data Index: 176043 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0509. Min Act: -0.0001

Data Index: 929286 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0504. Min Act: -0.0001

Data Index: 1062179 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0478. Min Act: -0.0001

Data Index: 521704 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0469. Min Act: -0.0001

Data Index: 760051 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0468. Min Act: -0.0001

Data Index: 608769 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1595551 (Python Code)

Max Activating Token Index: 321

Text #9

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0466. Min Act: -0.0001

Data Index: 1479134 (Python Code)

Max Activating Token Index: 180

Text #10

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0451. Min Act: -0.0001

Data Index: 663199 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0461. Min Act: -0.0001

Data Index: 1028129 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0449. Min Act: -0.0001

Data Index: 1128985 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0452. Min Act: -0.0001

Data Index: 227028 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0446. Min Act: -0.0002

Data Index: 332154 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0443. Min Act: -0.0001

Data Index: 569106 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0448. Min Act: -0.0001

Data Index: 504408 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0435. Min Act: -0.0001

Data Index: 960685 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0440. Min Act: -0.0001

Data Index: 300549 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0446. Min Act: -0.0001

Data Index: 1030137 (C4 (Web Text))

Max Activating Token Index: 85