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

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

Neuron 1749 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0523. Min Act: -0.0003

Data Index: 647206 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0543. Min Act: -0.0003

Data Index: 286082 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1131801 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0541. Min Act: -0.0003

Data Index: 1265096 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0520. Min Act: -0.0003

Data Index: 517661 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1053351 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0514. Min Act: -0.0003

Data Index: 662901 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0495. Min Act: -0.0003

Data Index: 1170250 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0512. Min Act: -0.0003

Data Index: 1249695 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0493. Min Act: -0.0003

Data Index: 672394 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0455. Min Act: -0.0003

Data Index: 249247 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0420. Min Act: -0.0003

Data Index: 268654 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0468. Min Act: -0.0003

Data Index: 8283 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0460. Min Act: -0.0003

Data Index: 686218 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0514. Min Act: -0.0003

Data Index: 597790 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0470. Min Act: -0.0003

Data Index: 492265 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0425. Min Act: -0.0003

Data Index: 851827 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1018754 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0480. Min Act: -0.0003

Data Index: 229369 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0543. Min Range: -0.0543

Max Act: 0.0462. Min Act: -0.0003

Data Index: 606288 (C4 (Web Text))

Max Activating Token Index: 1023