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

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

Neuron 3568 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0826. Min Act: -0.0001

Data Index: 311007 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0725. Min Act: -0.0001

Data Index: 33947 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0686. Min Act: -0.0001

Data Index: 539223 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0643. Min Act: -0.0002

Data Index: 324154 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0631. Min Act: -0.0002

Data Index: 786453 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0679. Min Act: -0.0001

Data Index: 699881 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0550. Min Act: -0.0002

Data Index: 377862 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1333522 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0547. Min Act: -0.0002

Data Index: 35843 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0533. Min Act: -0.0001

Data Index: 965118 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0499. Min Act: -0.0001

Data Index: 903464 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1157298 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0479. Min Act: -0.0002

Data Index: 488555 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0489. Min Act: -0.0001

Data Index: 51681 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0460. Min Act: -0.0002

Data Index: 916311 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0451. Min Act: -0.0002

Data Index: 29975 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0490. Min Act: -0.0001

Data Index: 672032 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0466. Min Act: -0.0002

Data Index: 259779 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1190289 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0471. Min Act: -0.0001

Data Index: 916290 (C4 (Web Text))

Max Activating Token Index: 864