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

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

Neuron 1446 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: 0.9715. Min Range: -0.9715

Max Act: 0.9715. Min Act: -0.0000

Data Index: 707327 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8960. Min Act: -0.0000

Data Index: 582761 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8866. Min Act: -0.0001

Data Index: 211692 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.7864. Min Act: -0.0000

Data Index: 3439 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8039. Min Act: -0.0000

Data Index: 99948 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8217. Min Act: 0.0001

Data Index: 1223150 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.8127. Min Act: -0.0001

Data Index: 334601 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.7741. Min Act: -0.0000

Data Index: 934675 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.7404. Min Act: -0.0000

Data Index: 311480 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.7294. Min Act: -0.0000

Data Index: 1019776 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.7267. Min Act: -0.0000

Data Index: 745822 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.7939. Min Act: -0.0000

Data Index: 1099148 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.7381. Min Act: -0.0000

Data Index: 31559 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.7108. Min Act: -0.0000

Data Index: 775357 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.7341. Min Act: -0.0000

Data Index: 282052 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.7289. Min Act: -0.0000

Data Index: 582771 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.7192. Min Act: -0.0001

Data Index: 207739 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.6398. Min Act: -0.0000

Data Index: 452130 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.7068. Min Act: 0.0001

Data Index: 96453 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.9715. Min Range: -0.9715

Max Act: 0.6957. Min Act: -0.0000

Data Index: 496227 (C4 (Web Text))

Max Activating Token Index: 417