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

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

Neuron 527 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8680. Min Range: -1.8680

Max Act: 1.8680. Min Act: -0.0000

Data Index: 422388 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 1.8680. Min Range: -1.8680

Max Act: 1.2057. Min Act: -0.0000

Data Index: 1290701 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 1.8680. Min Range: -1.8680

Max Act: 1.2494. Min Act: -0.0000

Data Index: 282825 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 1.8680. Min Range: -1.8680

Max Act: 0.9475. Min Act: -0.0000

Data Index: 1056946 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 1.8680. Min Range: -1.8680

Max Act: 0.8272. Min Act: -0.0000

Data Index: 297699 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 1.8680. Min Range: -1.8680

Max Act: 0.8460. Min Act: -0.0000

Data Index: 756275 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 1.8680. Min Range: -1.8680

Max Act: 0.9416. Min Act: -0.0000

Data Index: 787388 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 1.8680. Min Range: -1.8680

Max Act: 0.8036. Min Act: -0.0000

Data Index: 138861 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 1.8680. Min Range: -1.8680

Max Act: 0.7879. Min Act: -0.0000

Data Index: 1032396 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 1.8680. Min Range: -1.8680

Max Act: 0.7189. Min Act: -0.0000

Data Index: 162754 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 1.8680. Min Range: -1.8680

Max Act: 0.7693. Min Act: -0.0000

Data Index: 888212 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 1.8680. Min Range: -1.8680

Max Act: 0.7313. Min Act: -0.0000

Data Index: 1272547 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 1.8680. Min Range: -1.8680

Max Act: 0.7051. Min Act: -0.0000

Data Index: 530764 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 1.8680. Min Range: -1.8680

Max Act: 0.7444. Min Act: -0.0000

Data Index: 47904 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 1.8680. Min Range: -1.8680

Max Act: 0.7224. Min Act: -0.0000

Data Index: 8437 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 1.8680. Min Range: -1.8680

Max Act: 0.7758. Min Act: -0.0000

Data Index: 537367 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 1.8680. Min Range: -1.8680

Max Act: 0.7662. Min Act: -0.0000

Data Index: 1108936 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 1.8680. Min Range: -1.8680

Max Act: 0.7279. Min Act: -0.0000

Data Index: 209731 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 1.8680. Min Range: -1.8680

Max Act: 0.7217. Min Act: -0.0000

Data Index: 690336 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 1.8680. Min Range: -1.8680

Max Act: 0.7949. Min Act: -0.0000

Data Index: 895069 (C4 (Web Text))

Max Activating Token Index: 867