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

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

Neuron 5806 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: 3.0218. Min Range: -3.0218

Max Act: 3.0218. Min Act: -0.0000

Data Index: 683811 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 3.0218. Min Range: -3.0218

Max Act: 2.8302. Min Act: -0.0000

Data Index: 980557 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 3.0218. Min Range: -3.0218

Max Act: 2.7569. Min Act: -0.0000

Data Index: 725892 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 3.0218. Min Range: -3.0218

Max Act: 2.8806. Min Act: -0.0000

Data Index: 934805 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 3.0218. Min Range: -3.0218

Max Act: 2.7194. Min Act: -0.0000

Data Index: 653813 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 3.0218. Min Range: -3.0218

Max Act: 2.6358. Min Act: -0.0000

Data Index: 14199 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 3.0218. Min Range: -3.0218

Max Act: 2.5704. Min Act: -0.0000

Data Index: 18176 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 3.0218. Min Range: -3.0218

Max Act: 2.4220. Min Act: -0.0000

Data Index: 762218 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 3.0218. Min Range: -3.0218

Max Act: 2.4122. Min Act: -0.0000

Data Index: 1144072 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 3.0218. Min Range: -3.0218

Max Act: 2.3342. Min Act: -0.0000

Data Index: 895820 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 3.0218. Min Range: -3.0218

Max Act: 2.3946. Min Act: -0.0000

Data Index: 1600323 (Python Code)

Max Activating Token Index: 570

Text #11

Max Range: 3.0218. Min Range: -3.0218

Max Act: 2.3909. Min Act: -0.0000

Data Index: 1576805 (Python Code)

Max Activating Token Index: 522

Text #12

Max Range: 3.0218. Min Range: -3.0218

Max Act: 2.2909. Min Act: -0.0000

Data Index: 745739 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 3.0218. Min Range: -3.0218

Max Act: 2.2277. Min Act: -0.0000

Data Index: 443802 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 3.0218. Min Range: -3.0218

Max Act: 2.2098. Min Act: -0.0000

Data Index: 872277 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 3.0218. Min Range: -3.0218

Max Act: 2.0926. Min Act: -0.0000

Data Index: 1041809 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 3.0218. Min Range: -3.0218

Max Act: 2.1908. Min Act: -0.0000

Data Index: 706440 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 3.0218. Min Range: -3.0218

Max Act: 2.2705. Min Act: -0.0000

Data Index: 622224 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 3.0218. Min Range: -3.0218

Max Act: 2.1634. Min Act: -0.0000

Data Index: 1480071 (Python Code)

Max Activating Token Index: 217

Text #19

Max Range: 3.0218. Min Range: -3.0218

Max Act: 2.0317. Min Act: -0.0000

Data Index: 1380372 (Python Code)

Max Activating Token Index: 298