Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 979 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0543. Min Act: -0.0006

Data Index: 759093 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0522. Min Act: -0.0006

Data Index: 892547 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0006

Data Index: 1121383 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0511. Min Act: -0.0006

Data Index: 1005321 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0508. Min Act: -0.0006

Data Index: 238859 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0502. Min Act: -0.0006

Data Index: 416853 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0503. Min Act: -0.0006

Data Index: 1299248 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0499. Min Act: -0.0006

Data Index: 1232194 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0489. Min Act: -0.0006

Data Index: 118350 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0507. Min Act: -0.0006

Data Index: 256534 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0510. Min Act: -0.0006

Data Index: 413229 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0490. Min Act: -0.0006

Data Index: 200467 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0476. Min Act: -0.0006

Data Index: 392576 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0486. Min Act: -0.0006

Data Index: 225295 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0486. Min Act: -0.0006

Data Index: 319625 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0474. Min Act: -0.0006

Data Index: 16035 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0482. Min Act: -0.0006

Data Index: 1318196 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0482. Min Act: -0.0006

Data Index: 321770 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0478. Min Act: -0.0006

Data Index: 137266 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0476. Min Act: -0.0006

Data Index: 269209 (C4 (Web Text))

Max Activating Token Index: 774