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

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

Neuron 434 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.2885. Min Act: -0.0000

Data Index: 1444621 (Python Code)

Max Activating Token Index: 64

Text #1

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.2296. Min Act: -0.0000

Data Index: 1361242 (Python Code)

Max Activating Token Index: 626

Text #2

Max Range: 3.2885. Min Range: -3.2885

Max Act: 2.8117. Min Act: -0.0000

Data Index: 746553 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.2265. Min Act: -0.0000

Data Index: 1497135 (Python Code)

Max Activating Token Index: 921

Text #4

Max Range: 3.2885. Min Range: -3.2885

Max Act: 2.5841. Min Act: -0.0000

Data Index: 564756 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 3.2885. Min Range: -3.2885

Max Act: 3.1371. Min Act: -0.0000

Data Index: 1230664 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 3.2885. Min Range: -3.2885

Max Act: 2.6756. Min Act: -0.0000

Data Index: 1362140 (Python Code)

Max Activating Token Index: 316

Text #7

Max Range: 3.2885. Min Range: -3.2885

Max Act: 2.8005. Min Act: -0.0000

Data Index: 1623138 (Python Code)

Max Activating Token Index: 647

Text #8

Max Range: 3.2885. Min Range: -3.2885

Max Act: 2.9079. Min Act: -0.0000

Data Index: 47419 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 3.2885. Min Range: -3.2885

Max Act: 2.6600. Min Act: -0.0000

Data Index: 1426636 (Python Code)

Max Activating Token Index: 304

Text #10

Max Range: 3.2885. Min Range: -3.2885

Max Act: 2.5043. Min Act: -0.0000

Data Index: 1591299 (Python Code)

Max Activating Token Index: 243

Text #11

Max Range: 3.2885. Min Range: -3.2885

Max Act: 2.7521. Min Act: -0.0000

Data Index: 1370207 (Python Code)

Max Activating Token Index: 408

Text #12

Max Range: 3.2885. Min Range: -3.2885

Max Act: 2.6019. Min Act: -0.0000

Data Index: 250849 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 3.2885. Min Range: -3.2885

Max Act: 2.5453. Min Act: -0.0000

Data Index: 1653228 (Python Code)

Max Activating Token Index: 91

Text #14

Max Range: 3.2885. Min Range: -3.2885

Max Act: 2.2941. Min Act: -0.0000

Data Index: 1433192 (Python Code)

Max Activating Token Index: 799

Text #15

Max Range: 3.2885. Min Range: -3.2885

Max Act: 2.4801. Min Act: -0.0000

Data Index: 710081 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 3.2885. Min Range: -3.2885

Max Act: 2.3446. Min Act: -0.0000

Data Index: 703498 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 3.2885. Min Range: -3.2885

Max Act: 2.4507. Min Act: -0.0000

Data Index: 1513254 (Python Code)

Max Activating Token Index: 473

Text #18

Max Range: 3.2885. Min Range: -3.2885

Max Act: 2.5212. Min Act: -0.0000

Data Index: 1438157 (Python Code)

Max Activating Token Index: 696

Text #19

Max Range: 3.2885. Min Range: -3.2885

Max Act: 2.5366. Min Act: -0.0000

Data Index: 1207138 (C4 (Web Text))

Max Activating Token Index: 457