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

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

Neuron 196 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7120. Min Range: -4.7120

Max Act: 4.7120. Min Act: -0.0000

Data Index: 1389985 (Python Code)

Max Activating Token Index: 84

Text #1

Max Range: 4.7120. Min Range: -4.7120

Max Act: 4.3680. Min Act: 0.0000

Data Index: 704504 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.6390. Min Act: -0.0000

Data Index: 1536745 (Python Code)

Max Activating Token Index: 317

Text #3

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.3876. Min Act: -0.0000

Data Index: 1522557 (Python Code)

Max Activating Token Index: 339

Text #4

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.2294. Min Act: -0.0000

Data Index: 1318008 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.1585. Min Act: -0.0000

Data Index: 1479573 (Python Code)

Max Activating Token Index: 1017

Text #6

Max Range: 4.7120. Min Range: -4.7120

Max Act: 2.9954. Min Act: -0.0000

Data Index: 1479069 (Python Code)

Max Activating Token Index: 306

Text #7

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.1442. Min Act: -0.0000

Data Index: 1617012 (Python Code)

Max Activating Token Index: 722

Text #8

Max Range: 4.7120. Min Range: -4.7120

Max Act: 2.6487. Min Act: -0.0000

Data Index: 251740 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 4.7120. Min Range: -4.7120

Max Act: 2.8695. Min Act: -0.0000

Data Index: 1385553 (Python Code)

Max Activating Token Index: 566

Text #10

Max Range: 4.7120. Min Range: -4.7120

Max Act: 3.0064. Min Act: -0.0000

Data Index: 1631184 (Python Code)

Max Activating Token Index: 983

Text #11

Max Range: 4.7120. Min Range: -4.7120

Max Act: 2.7314. Min Act: -0.0000

Data Index: 1271081 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 4.7120. Min Range: -4.7120

Max Act: 2.4974. Min Act: -0.0000

Data Index: 985449 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 4.7120. Min Range: -4.7120

Max Act: 2.6052. Min Act: -0.0000

Data Index: 1461573 (Python Code)

Max Activating Token Index: 40

Text #14

Max Range: 4.7120. Min Range: -4.7120

Max Act: 2.7062. Min Act: 0.0000

Data Index: 1013355 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 4.7120. Min Range: -4.7120

Max Act: 2.4115. Min Act: -0.0000

Data Index: 1492120 (Python Code)

Max Activating Token Index: 269

Text #16

Max Range: 4.7120. Min Range: -4.7120

Max Act: 2.4371. Min Act: -0.0000

Data Index: 139523 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 4.7120. Min Range: -4.7120

Max Act: 2.4381. Min Act: -0.0000

Data Index: 1471791 (Python Code)

Max Activating Token Index: 331

Text #18

Max Range: 4.7120. Min Range: -4.7120

Max Act: 2.3951. Min Act: -0.0000

Data Index: 1367541 (Python Code)

Max Activating Token Index: 567

Text #19

Max Range: 4.7120. Min Range: -4.7120

Max Act: 2.1291. Min Act: -0.0000

Data Index: 1387217 (Python Code)

Max Activating Token Index: 583