Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3589 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0726. Min Range: -1.0726

Max Act: 1.0443. Min Act: -0.0000

Data Index: 663262 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 1.0726. Min Range: -1.0726

Max Act: 1.0726. Min Act: -0.0000

Data Index: 776783 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 1.0726. Min Range: -1.0726

Max Act: 1.0220. Min Act: -0.0000

Data Index: 524987 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 1.0726. Min Range: -1.0726

Max Act: 1.0560. Min Act: -0.0000

Data Index: 318923 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9543. Min Act: -0.0000

Data Index: 595303 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8877. Min Act: -0.0000

Data Index: 131693 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9125. Min Act: -0.0000

Data Index: 210928 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9057. Min Act: -0.0000

Data Index: 396192 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1297202 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9121. Min Act: -0.0000

Data Index: 1291093 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9120. Min Act: -0.0000

Data Index: 505662 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9119. Min Act: -0.0000

Data Index: 940037 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8573. Min Act: -0.0000

Data Index: 864457 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8878. Min Act: -0.0000

Data Index: 174543 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8779. Min Act: -0.0000

Data Index: 605541 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8678. Min Act: -0.0000

Data Index: 1160095 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8641. Min Act: -0.0000

Data Index: 993184 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8490. Min Act: -0.0000

Data Index: 648440 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8410. Min Act: -0.0000

Data Index: 392045 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8369. Min Act: -0.0000

Data Index: 907249 (C4 (Web Text))

Max Activating Token Index: 727