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

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

Neuron 3432 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.7126. Min Act: -0.0001

Data Index: 218779 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.6239. Min Act: -0.0001

Data Index: 536489 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.6047. Min Act: -0.0001

Data Index: 307506 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4585. Min Act: -0.0001

Data Index: 202620 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4987. Min Act: -0.0001

Data Index: 241557 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4382. Min Act: -0.0001

Data Index: 1185990 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4558. Min Act: -0.0001

Data Index: 1327257 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4016. Min Act: -0.0001

Data Index: 902754 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4275. Min Act: -0.0001

Data Index: 897931 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4139. Min Act: -0.0001

Data Index: 1361936 (Python Code)

Max Activating Token Index: 406

Text #10

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4117. Min Act: -0.0001

Data Index: 670336 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.3863. Min Act: -0.0001

Data Index: 683309 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4072. Min Act: -0.0001

Data Index: 435532 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.3449. Min Act: -0.0001

Data Index: 274474 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.3852. Min Act: -0.0001

Data Index: 1442520 (Python Code)

Max Activating Token Index: 749

Text #15

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4357. Min Act: -0.0001

Data Index: 672505 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.3830. Min Act: -0.0001

Data Index: 89903 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.3940. Min Act: -0.0001

Data Index: 1363958 (Python Code)

Max Activating Token Index: 352

Text #18

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.4032. Min Act: -0.0001

Data Index: 1257571 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.7126. Min Range: -0.7126

Max Act: 0.3102. Min Act: -0.0001

Data Index: 1076623 (C4 (Web Text))

Max Activating Token Index: 597