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

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

Neuron 5541 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: 0.4561. Min Range: -0.4561

Max Act: 0.4561. Min Act: -0.0000

Data Index: 409703 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3877. Min Act: -0.0000

Data Index: 756460 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3532. Min Act: -0.0000

Data Index: 1251049 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1293816 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3360. Min Act: -0.0000

Data Index: 802320 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3094. Min Act: -0.0000

Data Index: 56125 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3149. Min Act: -0.0000

Data Index: 261323 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2969. Min Act: -0.0000

Data Index: 478875 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3249. Min Act: -0.0000

Data Index: 1327632 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2882. Min Act: -0.0000

Data Index: 943343 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2697. Min Act: -0.0000

Data Index: 1074899 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2957. Min Act: -0.0000

Data Index: 410428 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3046. Min Act: -0.0000

Data Index: 811315 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3007. Min Act: -0.0000

Data Index: 262292 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1544628 (Python Code)

Max Activating Token Index: 658

Text #15

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1162243 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2806. Min Act: -0.0000

Data Index: 224891 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2706. Min Act: -0.0000

Data Index: 672803 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2854. Min Act: -0.0000

Data Index: 655034 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2104. Min Act: -0.0000

Data Index: 122335 (C4 (Web Text))

Max Activating Token Index: 440