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

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

Neuron 3159 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.0644. Min Range: -8.0644

Max Act: 7.8630. Min Act: -0.0001

Data Index: 215247 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 8.0644. Min Range: -8.0644

Max Act: 7.9363. Min Act: -0.0001

Data Index: 1045325 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 8.0644. Min Range: -8.0644

Max Act: 8.0644. Min Act: -0.0001

Data Index: 618894 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 8.0644. Min Range: -8.0644

Max Act: 7.5533. Min Act: -0.0001

Data Index: 900388 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 8.0644. Min Range: -8.0644

Max Act: 7.7546. Min Act: -0.0001

Data Index: 1182512 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 8.0644. Min Range: -8.0644

Max Act: 7.8348. Min Act: -0.0001

Data Index: 713710 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 8.0644. Min Range: -8.0644

Max Act: 7.8458. Min Act: -0.0001

Data Index: 990875 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 8.0644. Min Range: -8.0644

Max Act: 7.6281. Min Act: -0.0001

Data Index: 303762 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 8.0644. Min Range: -8.0644

Max Act: 7.7593. Min Act: -0.0001

Data Index: 647395 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 8.0644. Min Range: -8.0644

Max Act: 7.5724. Min Act: -0.0001

Data Index: 1012662 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 8.0644. Min Range: -8.0644

Max Act: 7.2346. Min Act: -0.0001

Data Index: 66395 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 8.0644. Min Range: -8.0644

Max Act: 7.3786. Min Act: -0.0001

Data Index: 702914 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 8.0644. Min Range: -8.0644

Max Act: 7.5283. Min Act: -0.0001

Data Index: 1343117 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 8.0644. Min Range: -8.0644

Max Act: 7.3145. Min Act: -0.0001

Data Index: 971367 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 8.0644. Min Range: -8.0644

Max Act: 7.2846. Min Act: -0.0001

Data Index: 286938 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 8.0644. Min Range: -8.0644

Max Act: 7.2674. Min Act: -0.0001

Data Index: 510190 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 8.0644. Min Range: -8.0644

Max Act: 6.9318. Min Act: -0.0001

Data Index: 201556 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 8.0644. Min Range: -8.0644

Max Act: 7.3613. Min Act: -0.0001

Data Index: 914991 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 8.0644. Min Range: -8.0644

Max Act: 7.3025. Min Act: -0.0001

Data Index: 155267 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 8.0644. Min Range: -8.0644

Max Act: 7.1510. Min Act: -0.0001

Data Index: 791125 (C4 (Web Text))

Max Activating Token Index: 408