Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4630 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1610. Min Range: -3.1610

Max Act: 3.1196. Min Act: -0.0000

Data Index: 176633 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 3.1610. Min Range: -3.1610

Max Act: 3.0652. Min Act: -0.0000

Data Index: 201199 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 3.1610. Min Range: -3.1610

Max Act: 3.0591. Min Act: -0.0000

Data Index: 261535 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 3.1610. Min Range: -3.1610

Max Act: 3.1522. Min Act: -0.0000

Data Index: 1206513 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 3.1610. Min Range: -3.1610

Max Act: 3.1610. Min Act: -0.0000

Data Index: 470674 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 3.1610. Min Range: -3.1610

Max Act: 2.7504. Min Act: -0.0000

Data Index: 1307411 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 3.1610. Min Range: -3.1610

Max Act: 2.8864. Min Act: -0.0000

Data Index: 211013 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 3.1610. Min Range: -3.1610

Max Act: 2.6275. Min Act: -0.0000

Data Index: 1222855 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 3.1610. Min Range: -3.1610

Max Act: 2.6345. Min Act: -0.0000

Data Index: 158998 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 3.1610. Min Range: -3.1610

Max Act: 2.6525. Min Act: -0.0000

Data Index: 247210 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 3.1610. Min Range: -3.1610

Max Act: 2.3845. Min Act: -0.0000

Data Index: 311020 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 3.1610. Min Range: -3.1610

Max Act: 2.3524. Min Act: -0.0000

Data Index: 759147 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 3.1610. Min Range: -3.1610

Max Act: 2.0511. Min Act: -0.0000

Data Index: 498225 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 3.1610. Min Range: -3.1610

Max Act: 1.9841. Min Act: -0.0000

Data Index: 694378 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 3.1610. Min Range: -3.1610

Max Act: 1.8769. Min Act: -0.0000

Data Index: 336809 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 3.1610. Min Range: -3.1610

Max Act: 1.8040. Min Act: -0.0000

Data Index: 1127005 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 3.1610. Min Range: -3.1610

Max Act: 1.7620. Min Act: -0.0000

Data Index: 460666 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 3.1610. Min Range: -3.1610

Max Act: 1.7057. Min Act: -0.0000

Data Index: 135645 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 3.1610. Min Range: -3.1610

Max Act: 1.6888. Min Act: -0.0000

Data Index: 455172 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 3.1610. Min Range: -3.1610

Max Act: 1.5290. Min Act: -0.0000

Data Index: 15351 (C4 (Web Text))

Max Activating Token Index: 207