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

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

Neuron 2916 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: 0.9044. Min Range: -0.9044

Max Act: 0.9044. Min Act: -0.0001

Data Index: 230210 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.8734. Min Act: -0.0001

Data Index: 959119 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.8495. Min Act: -0.0001

Data Index: 78550 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.7594. Min Act: -0.0002

Data Index: 47636 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.8493. Min Act: -0.0002

Data Index: 204105 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.8261. Min Act: -0.0001

Data Index: 1215661 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.8189. Min Act: -0.0002

Data Index: 959023 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.7906. Min Act: -0.0002

Data Index: 176683 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.7805. Min Act: -0.0001

Data Index: 608085 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.8192. Min Act: -0.0002

Data Index: 600538 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.7677. Min Act: -0.0002

Data Index: 878463 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.8141. Min Act: -0.0002

Data Index: 328368 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.8179. Min Act: -0.0002

Data Index: 492360 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.8170. Min Act: -0.0001

Data Index: 924403 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.7468. Min Act: -0.0002

Data Index: 852259 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.8546. Min Act: -0.0001

Data Index: 428749 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.7850. Min Act: -0.0001

Data Index: 708746 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.7802. Min Act: -0.0001

Data Index: 680864 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.8011. Min Act: -0.0002

Data Index: 255457 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.8159. Min Act: -0.0002

Data Index: 1287185 (C4 (Web Text))

Max Activating Token Index: 593