Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2747 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3599. Min Act: -0.0000

Data Index: 13909 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3815. Min Act: 0.0000

Data Index: 1288924 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3664. Min Act: -0.0000

Data Index: 992565 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3402. Min Act: -0.0000

Data Index: 603121 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3225. Min Act: -0.0000

Data Index: 562149 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1340033 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3069. Min Act: 0.0000

Data Index: 299754 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3089. Min Act: -0.0001

Data Index: 875526 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3040. Min Act: -0.0001

Data Index: 198976 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2914. Min Act: -0.0000

Data Index: 25335 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3004. Min Act: 0.0000

Data Index: 1196663 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3009. Min Act: -0.0001

Data Index: 275014 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2980. Min Act: -0.0000

Data Index: 637810 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2915. Min Act: -0.0000

Data Index: 714681 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2937. Min Act: -0.0000

Data Index: 376570 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2800. Min Act: -0.0000

Data Index: 376444 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1226293 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2820. Min Act: -0.0001

Data Index: 1136082 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2991. Min Act: -0.0001

Data Index: 416006 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2870. Min Act: -0.0000

Data Index: 772662 (C4 (Web Text))

Max Activating Token Index: 526