Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1367 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.6594. Min Act: -0.0002

Data Index: 359153 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5705. Min Act: -0.0002

Data Index: 626498 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5833. Min Act: -0.0002

Data Index: 59381 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5178. Min Act: -0.0002

Data Index: 809430 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.5969. Min Act: -0.0001

Data Index: 792820 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4880. Min Act: -0.0002

Data Index: 34864 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.2187. Min Act: -0.0002

Data Index: 156705 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4889. Min Act: -0.0001

Data Index: 875188 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4441. Min Act: -0.0002

Data Index: 797428 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4535. Min Act: -0.0002

Data Index: 792076 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4610. Min Act: -0.0002

Data Index: 241513 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.4394. Min Act: -0.0002

Data Index: 638892 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.2803. Min Act: -0.0002

Data Index: 467025 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.1586. Min Act: -0.0002

Data Index: 209828 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3321. Min Act: -0.0002

Data Index: 913276 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3345. Min Act: -0.0002

Data Index: 343925 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3571. Min Act: -0.0002

Data Index: 672908 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3387. Min Act: -0.0002

Data Index: 1072091 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3120. Min Act: -0.0002

Data Index: 43929 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.6594. Min Range: -0.6594

Max Act: 0.3381. Min Act: -0.0002

Data Index: 530541 (C4 (Web Text))

Max Activating Token Index: 581