Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2597 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.6011. Min Act: -0.0000

Data Index: 1603447 (Python Code)

Max Activating Token Index: 745

Text #1

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.6001. Min Act: -0.0000

Data Index: 39782 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1421077 (Python Code)

Max Activating Token Index: 831

Text #3

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1644092 (Python Code)

Max Activating Token Index: 787

Text #4

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.5408. Min Act: -0.0000

Data Index: 1266257 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.5264. Min Act: -0.0000

Data Index: 752588 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.4996. Min Act: -0.0000

Data Index: 1403544 (Python Code)

Max Activating Token Index: 183

Text #7

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1501112 (Python Code)

Max Activating Token Index: 527

Text #8

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.4842. Min Act: -0.0000

Data Index: 736214 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1560539 (Python Code)

Max Activating Token Index: 557

Text #10

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1584894 (Python Code)

Max Activating Token Index: 696

Text #11

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.4522. Min Act: -0.0000

Data Index: 1533027 (Python Code)

Max Activating Token Index: 550

Text #12

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.4789. Min Act: -0.0000

Data Index: 96538 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1649926 (Python Code)

Max Activating Token Index: 216

Text #14

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.4644. Min Act: -0.0000

Data Index: 1424822 (Python Code)

Max Activating Token Index: 129

Text #15

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.4299. Min Act: -0.0000

Data Index: 1539036 (Python Code)

Max Activating Token Index: 907

Text #16

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.4575. Min Act: -0.0000

Data Index: 761548 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.4377. Min Act: -0.0000

Data Index: 365435 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.4483. Min Act: -0.0000

Data Index: 40437 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1182312 (C4 (Web Text))

Max Activating Token Index: 97