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

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

Neuron 2330 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: 2.2738. Min Range: -2.2738

Max Act: 2.2738. Min Act: -0.0000

Data Index: 401753 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 2.2738. Min Range: -2.2738

Max Act: 1.6740. Min Act: -0.0000

Data Index: 1420164 (Python Code)

Max Activating Token Index: 559

Text #2

Max Range: 2.2738. Min Range: -2.2738

Max Act: 1.6790. Min Act: -0.0000

Data Index: 1499522 (Python Code)

Max Activating Token Index: 482

Text #3

Max Range: 2.2738. Min Range: -2.2738

Max Act: 1.7676. Min Act: -0.0000

Data Index: 1522395 (Python Code)

Max Activating Token Index: 314

Text #4

Max Range: 2.2738. Min Range: -2.2738

Max Act: 1.7317. Min Act: -0.0000

Data Index: 1512163 (Python Code)

Max Activating Token Index: 285

Text #5

Max Range: 2.2738. Min Range: -2.2738

Max Act: 1.6799. Min Act: -0.0000

Data Index: 1377883 (Python Code)

Max Activating Token Index: 67

Text #6

Max Range: 2.2738. Min Range: -2.2738

Max Act: 1.6388. Min Act: -0.0000

Data Index: 954643 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 2.2738. Min Range: -2.2738

Max Act: 1.6607. Min Act: -0.0000

Data Index: 515885 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 2.2738. Min Range: -2.2738

Max Act: 1.5072. Min Act: -0.0000

Data Index: 193443 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 2.2738. Min Range: -2.2738

Max Act: 1.5930. Min Act: -0.0000

Data Index: 1634112 (Python Code)

Max Activating Token Index: 1011

Text #10

Max Range: 2.2738. Min Range: -2.2738

Max Act: 1.5885. Min Act: -0.0000

Data Index: 1392237 (Python Code)

Max Activating Token Index: 312

Text #11

Max Range: 2.2738. Min Range: -2.2738

Max Act: 1.5670. Min Act: -0.0000

Data Index: 1400781 (Python Code)

Max Activating Token Index: 488

Text #12

Max Range: 2.2738. Min Range: -2.2738

Max Act: 1.6451. Min Act: -0.0000

Data Index: 399700 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 2.2738. Min Range: -2.2738

Max Act: 1.5581. Min Act: -0.0000

Data Index: 837385 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 2.2738. Min Range: -2.2738

Max Act: 1.5989. Min Act: -0.0000

Data Index: 1484878 (Python Code)

Max Activating Token Index: 353

Text #15

Max Range: 2.2738. Min Range: -2.2738

Max Act: 1.5928. Min Act: -0.0000

Data Index: 1420996 (Python Code)

Max Activating Token Index: 274

Text #16

Max Range: 2.2738. Min Range: -2.2738

Max Act: 1.5107. Min Act: -0.0000

Data Index: 1378060 (Python Code)

Max Activating Token Index: 270

Text #17

Max Range: 2.2738. Min Range: -2.2738

Max Act: 1.5192. Min Act: -0.0000

Data Index: 1633516 (Python Code)

Max Activating Token Index: 501

Text #18

Max Range: 2.2738. Min Range: -2.2738

Max Act: 1.5057. Min Act: -0.0000

Data Index: 1202643 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 2.2738. Min Range: -2.2738

Max Act: 1.4593. Min Act: -0.0000

Data Index: 1575151 (Python Code)

Max Activating Token Index: 321