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

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

Neuron 1506 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.8544. Min Act: -0.0001

Data Index: 398231 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.7276. Min Act: -0.0000

Data Index: 675787 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.6830. Min Act: -0.0000

Data Index: 69245 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.7064. Min Act: -0.0001

Data Index: 172291 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.6567. Min Act: -0.0000

Data Index: 968176 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.6478. Min Act: -0.0000

Data Index: 588168 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.5907. Min Act: -0.0001

Data Index: 838794 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1215271 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1160517 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1980 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.5154. Min Act: -0.0000

Data Index: 990877 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.5130. Min Act: -0.0000

Data Index: 127990 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.5413. Min Act: -0.0000

Data Index: 270221 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.5193. Min Act: -0.0000

Data Index: 1034103 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.4911. Min Act: -0.0000

Data Index: 145207 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.5361. Min Act: -0.0000

Data Index: 830597 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1219651 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.5128. Min Act: -0.0001

Data Index: 1270605 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.4607. Min Act: -0.0000

Data Index: 719088 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1291493 (C4 (Web Text))

Max Activating Token Index: 471