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

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

Neuron 1046 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: 1.5007. Min Range: -1.5007

Max Act: 1.5007. Min Act: -0.0001

Data Index: 705206 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 1.5007. Min Range: -1.5007

Max Act: 1.2437. Min Act: -0.0001

Data Index: 666452 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 1.5007. Min Range: -1.5007

Max Act: 1.0157. Min Act: -0.0001

Data Index: 1173771 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 1.5007. Min Range: -1.5007

Max Act: 1.0582. Min Act: -0.0001

Data Index: 1301800 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.9608. Min Act: -0.0001

Data Index: 153183 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.9539. Min Act: -0.0001

Data Index: 1027625 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.9290. Min Act: -0.0001

Data Index: 960429 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.9214. Min Act: -0.0001

Data Index: 942189 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.8970. Min Act: -0.0001

Data Index: 48302 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.8376. Min Act: -0.0001

Data Index: 385748 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.8566. Min Act: -0.0001

Data Index: 1130838 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.7942. Min Act: -0.0001

Data Index: 245661 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.8266. Min Act: -0.0001

Data Index: 680133 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.8196. Min Act: -0.0001

Data Index: 1054387 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.8372. Min Act: -0.0001

Data Index: 264317 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.7851. Min Act: -0.0001

Data Index: 1259025 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.7983. Min Act: -0.0000

Data Index: 397888 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.7659. Min Act: -0.0001

Data Index: 816928 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.7873. Min Act: -0.0001

Data Index: 725687 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 1.5007. Min Range: -1.5007

Max Act: 0.8090. Min Act: -0.0001

Data Index: 838114 (C4 (Web Text))

Max Activating Token Index: 299