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

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

Neuron 3268 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3072. Min Range: -4.3072

Max Act: 4.3072. Min Act: -0.0000

Data Index: 565654 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 4.3072. Min Range: -4.3072

Max Act: 3.6066. Min Act: -0.0001

Data Index: 1063995 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 4.3072. Min Range: -4.3072

Max Act: 2.5411. Min Act: -0.0000

Data Index: 1350693 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 4.3072. Min Range: -4.3072

Max Act: 2.2687. Min Act: -0.0001

Data Index: 174295 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 4.3072. Min Range: -4.3072

Max Act: 2.2380. Min Act: -0.0001

Data Index: 748939 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 4.3072. Min Range: -4.3072

Max Act: 2.3105. Min Act: -0.0000

Data Index: 754391 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 4.3072. Min Range: -4.3072

Max Act: 2.1594. Min Act: -0.0001

Data Index: 682276 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 4.3072. Min Range: -4.3072

Max Act: 2.2034. Min Act: -0.0001

Data Index: 61824 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 4.3072. Min Range: -4.3072

Max Act: 1.9646. Min Act: -0.0000

Data Index: 1361745 (Python Code)

Max Activating Token Index: 174

Text #9

Max Range: 4.3072. Min Range: -4.3072

Max Act: 2.1258. Min Act: -0.0001

Data Index: 1335586 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 4.3072. Min Range: -4.3072

Max Act: 2.0903. Min Act: -0.0001

Data Index: 1103031 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 4.3072. Min Range: -4.3072

Max Act: 1.8483. Min Act: -0.0001

Data Index: 416029 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 4.3072. Min Range: -4.3072

Max Act: 1.9189. Min Act: -0.0001

Data Index: 720120 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 4.3072. Min Range: -4.3072

Max Act: 1.9003. Min Act: -0.0001

Data Index: 369921 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 4.3072. Min Range: -4.3072

Max Act: 1.6785. Min Act: -0.0001

Data Index: 439793 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 4.3072. Min Range: -4.3072

Max Act: 1.7637. Min Act: -0.0000

Data Index: 313805 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 4.3072. Min Range: -4.3072

Max Act: 1.7076. Min Act: -0.0001

Data Index: 674528 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 4.3072. Min Range: -4.3072

Max Act: 1.7939. Min Act: -0.0001

Data Index: 1112284 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 4.3072. Min Range: -4.3072

Max Act: 1.6635. Min Act: -0.0001

Data Index: 486113 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 4.3072. Min Range: -4.3072

Max Act: 1.6690. Min Act: -0.0000

Data Index: 1162458 (C4 (Web Text))

Max Activating Token Index: 1019