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

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

Neuron 317 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: 0.0507. Min Range: -0.0507

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1050189 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1302625 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1072208 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1091955 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0498. Min Act: -0.0002

Data Index: 104698 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1388123 (Python Code)

Max Activating Token Index: 844

Text #6

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1168249 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1534560 (Python Code)

Max Activating Token Index: 8

Text #8

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0476. Min Act: -0.0002

Data Index: 804495 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1512574 (Python Code)

Max Activating Token Index: 242

Text #10

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0467. Min Act: -0.0002

Data Index: 922205 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0457. Min Act: -0.0003

Data Index: 1095960 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0461. Min Act: -0.0002

Data Index: 494217 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0454. Min Act: -0.0002

Data Index: 624601 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0452. Min Act: -0.0002

Data Index: 531529 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1400574 (Python Code)

Max Activating Token Index: 688

Text #16

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0441. Min Act: -0.0002

Data Index: 925477 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1149778 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1353938 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0439. Min Act: -0.0002

Data Index: 283775 (C4 (Web Text))

Max Activating Token Index: 271