Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1507 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.7354. Min Act: -0.0001

Data Index: 1318740 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.7005. Min Act: -0.0001

Data Index: 130749 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.5489. Min Act: -0.0001

Data Index: 586738 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.5754. Min Act: -0.0001

Data Index: 855258 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.6829. Min Act: -0.0001

Data Index: 524271 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.6682. Min Act: -0.0001

Data Index: 1168646 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.6589. Min Act: -0.0001

Data Index: 184315 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.4758. Min Act: -0.0001

Data Index: 666924 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.6000. Min Act: -0.0001

Data Index: 87262 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.5524. Min Act: -0.0001

Data Index: 166568 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.3956. Min Act: -0.0001

Data Index: 1128408 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.5897. Min Act: -0.0001

Data Index: 554096 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.5444. Min Act: -0.0001

Data Index: 1237 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.5040. Min Act: -0.0001

Data Index: 1267931 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.4459. Min Act: -0.0001

Data Index: 167106 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.4299. Min Act: -0.0001

Data Index: 24648 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.3879. Min Act: -0.0001

Data Index: 1000906 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.3858. Min Act: -0.0001

Data Index: 470345 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.3473. Min Act: -0.0001

Data Index: 576115 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 1.7354. Min Range: -1.7354

Max Act: 1.3124. Min Act: -0.0001

Data Index: 905872 (C4 (Web Text))

Max Activating Token Index: 856