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

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

Neuron 991 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.7638. Min Act: -0.0000

Data Index: 811527 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.7308. Min Act: -0.0001

Data Index: 733198 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.7246. Min Act: -0.0000

Data Index: 1114477 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6203. Min Act: -0.0000

Data Index: 511929 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1311055 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6203. Min Act: -0.0000

Data Index: 983485 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6641. Min Act: -0.0000

Data Index: 50453 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5986. Min Act: -0.0000

Data Index: 204137 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6139. Min Act: -0.0000

Data Index: 912496 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5673. Min Act: -0.0000

Data Index: 1013999 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5978. Min Act: -0.0000

Data Index: 434692 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6259. Min Act: -0.0000

Data Index: 865922 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6097. Min Act: -0.0000

Data Index: 794042 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5831. Min Act: -0.0001

Data Index: 542240 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5668. Min Act: -0.0000

Data Index: 288584 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5782. Min Act: -0.0000

Data Index: 909090 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6015. Min Act: -0.0001

Data Index: 894484 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5451. Min Act: -0.0001

Data Index: 840470 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6044. Min Act: -0.0000

Data Index: 278580 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5888. Min Act: -0.0001

Data Index: 718924 (C4 (Web Text))

Max Activating Token Index: 355