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

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

Neuron 4569 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: 2.7715. Min Range: -2.7715

Max Act: 2.7715. Min Act: -0.0000

Data Index: 686730 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 2.7715. Min Range: -2.7715

Max Act: 2.6446. Min Act: -0.0000

Data Index: 950314 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 2.7715. Min Range: -2.7715

Max Act: 2.5288. Min Act: -0.0000

Data Index: 893242 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 2.7715. Min Range: -2.7715

Max Act: 2.2081. Min Act: -0.0000

Data Index: 24686 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 2.7715. Min Range: -2.7715

Max Act: 2.3062. Min Act: -0.0000

Data Index: 1049390 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 2.7715. Min Range: -2.7715

Max Act: 2.3997. Min Act: -0.0000

Data Index: 1202480 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 2.7715. Min Range: -2.7715

Max Act: 2.2766. Min Act: -0.0000

Data Index: 666677 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 2.7715. Min Range: -2.7715

Max Act: 2.1254. Min Act: -0.0000

Data Index: 86323 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 2.7715. Min Range: -2.7715

Max Act: 2.0396. Min Act: -0.0000

Data Index: 670978 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 2.7715. Min Range: -2.7715

Max Act: 2.2660. Min Act: -0.0000

Data Index: 895366 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 2.7715. Min Range: -2.7715

Max Act: 2.1324. Min Act: -0.0000

Data Index: 460516 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 2.7715. Min Range: -2.7715

Max Act: 2.1233. Min Act: -0.0000

Data Index: 1111576 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 2.7715. Min Range: -2.7715

Max Act: 1.8889. Min Act: 0.0001

Data Index: 446343 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 2.7715. Min Range: -2.7715

Max Act: 2.1950. Min Act: -0.0000

Data Index: 489892 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 2.7715. Min Range: -2.7715

Max Act: 2.0673. Min Act: 0.0000

Data Index: 806174 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 2.7715. Min Range: -2.7715

Max Act: 2.0598. Min Act: -0.0000

Data Index: 481625 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 2.7715. Min Range: -2.7715

Max Act: 1.9347. Min Act: -0.0000

Data Index: 1233134 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 2.7715. Min Range: -2.7715

Max Act: 1.9350. Min Act: -0.0000

Data Index: 526998 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 2.7715. Min Range: -2.7715

Max Act: 2.0358. Min Act: -0.0000

Data Index: 833431 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 2.7715. Min Range: -2.7715

Max Act: 2.0220. Min Act: -0.0000

Data Index: 667215 (C4 (Web Text))

Max Activating Token Index: 526