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

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

Neuron 1590 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: 0.0503. Min Range: -0.0503

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1624462 (Python Code)

Max Activating Token Index: 45

Text #1

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1528860 (Python Code)

Max Activating Token Index: 112

Text #2

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1519650 (Python Code)

Max Activating Token Index: 44

Text #3

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0441. Min Act: -0.0001

Data Index: 1531815 (Python Code)

Max Activating Token Index: 17

Text #4

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0446. Min Act: -0.0001

Data Index: 1433121 (Python Code)

Max Activating Token Index: 826

Text #5

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0439. Min Act: -0.0001

Data Index: 1356738 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1593629 (Python Code)

Max Activating Token Index: 54

Text #7

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1428629 (Python Code)

Max Activating Token Index: 714

Text #8

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1553768 (Python Code)

Max Activating Token Index: 107

Text #9

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1593074 (Python Code)

Max Activating Token Index: 389

Text #10

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1595735 (Python Code)

Max Activating Token Index: 133

Text #11

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1403158 (Python Code)

Max Activating Token Index: 659

Text #12

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0423. Min Act: -0.0001

Data Index: 1472569 (Python Code)

Max Activating Token Index: 1002

Text #13

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0423. Min Act: -0.0001

Data Index: 1594152 (Python Code)

Max Activating Token Index: 93

Text #14

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0423. Min Act: -0.0001

Data Index: 1369602 (Python Code)

Max Activating Token Index: 91

Text #15

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0423. Min Act: -0.0001

Data Index: 1515247 (Python Code)

Max Activating Token Index: 155

Text #16

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1402320 (Python Code)

Max Activating Token Index: 1022

Text #17

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0418. Min Act: -0.0001

Data Index: 1452943 (Python Code)

Max Activating Token Index: 87

Text #18

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1464099 (Python Code)

Max Activating Token Index: 236

Text #19

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1522464 (Python Code)

Max Activating Token Index: 628