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

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

Neuron 2509 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: 0.2905. Min Range: -0.2905

Max Act: 0.2905. Min Act: -0.0000

Data Index: 1063790 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2876. Min Act: -0.0000

Data Index: 168804 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2642. Min Act: -0.0001

Data Index: 757542 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2793. Min Act: -0.0000

Data Index: 107685 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2548. Min Act: -0.0000

Data Index: 391379 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2414. Min Act: -0.0000

Data Index: 373772 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2564. Min Act: -0.0000

Data Index: 936371 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2468. Min Act: -0.0000

Data Index: 481200 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2373. Min Act: -0.0001

Data Index: 923126 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2282. Min Act: -0.0000

Data Index: 868995 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2483. Min Act: -0.0001

Data Index: 123590 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2321. Min Act: -0.0000

Data Index: 135401 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2191. Min Act: -0.0000

Data Index: 251268 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2117. Min Act: -0.0001

Data Index: 428446 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1067059 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2153. Min Act: -0.0000

Data Index: 652339 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2056. Min Act: -0.0000

Data Index: 1256949 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2020. Min Act: -0.0000

Data Index: 246634 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2105. Min Act: -0.0000

Data Index: 1297312 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2131. Min Act: -0.0001

Data Index: 1129012 (C4 (Web Text))

Max Activating Token Index: 656