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

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

Neuron 245 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: 0.0543. Min Range: -0.0543

Max Act: 0.0543. Min Act: -0.0002

Data Index: 590037 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0466. Min Act: -0.0002

Data Index: 631412 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1130791 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0433. Min Act: -0.0002

Data Index: 604426 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1383795 (Python Code)

Max Activating Token Index: 87

Text #5

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1547520 (Python Code)

Max Activating Token Index: 675

Text #6

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1593127 (Python Code)

Max Activating Token Index: 321

Text #7

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1613377 (Python Code)

Max Activating Token Index: 267

Text #8

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0415. Min Act: -0.0002

Data Index: 454991 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1247175 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0400. Min Act: -0.0002

Data Index: 249331 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1501554 (Python Code)

Max Activating Token Index: 362

Text #12

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1493073 (Python Code)

Max Activating Token Index: 1007

Text #13

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0390. Min Act: -0.0002

Data Index: 864380 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1385795 (Python Code)

Max Activating Token Index: 489

Text #15

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0386. Min Act: -0.0002

Data Index: 239092 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1550804 (Python Code)

Max Activating Token Index: 828

Text #17

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1383765 (Python Code)

Max Activating Token Index: 471

Text #18

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0394. Min Act: -0.0002

Data Index: 933056 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1555666 (Python Code)

Max Activating Token Index: 467