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

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

Neuron 1230 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.7497. Min Act: -0.0001

Data Index: 256049 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.7102. Min Act: -0.0001

Data Index: 527253 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6884. Min Act: -0.0001

Data Index: 1240304 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6698. Min Act: -0.0001

Data Index: 1171237 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6540. Min Act: -0.0001

Data Index: 408907 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6832. Min Act: -0.0001

Data Index: 289834 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6158. Min Act: -0.0001

Data Index: 1120615 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6369. Min Act: -0.0001

Data Index: 642848 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6575. Min Act: -0.0001

Data Index: 1273434 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6241. Min Act: -0.0001

Data Index: 1353947 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6000. Min Act: -0.0001

Data Index: 702790 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6276. Min Act: -0.0001

Data Index: 199683 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6413. Min Act: -0.0001

Data Index: 718344 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5963. Min Act: -0.0001

Data Index: 74407 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6022. Min Act: -0.0001

Data Index: 1343464 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5977. Min Act: -0.0001

Data Index: 1227818 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5950. Min Act: -0.0001

Data Index: 1348737 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5930. Min Act: -0.0001

Data Index: 1221934 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5891. Min Act: -0.0001

Data Index: 113591 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6340. Min Act: -0.0001

Data Index: 1059768 (C4 (Web Text))

Max Activating Token Index: 577