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

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

Neuron 2085 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.3030. Min Act: -0.0001

Data Index: 788131 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2826. Min Act: -0.0001

Data Index: 263613 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2690. Min Act: -0.0001

Data Index: 419372 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2772. Min Act: -0.0001

Data Index: 1048465 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2826. Min Act: -0.0001

Data Index: 227027 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2643. Min Act: -0.0001

Data Index: 573565 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2702. Min Act: -0.0001

Data Index: 1576401 (Python Code)

Max Activating Token Index: 256

Text #7

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2681. Min Act: -0.0001

Data Index: 1425203 (Python Code)

Max Activating Token Index: 528

Text #8

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2676. Min Act: -0.0001

Data Index: 619120 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2506. Min Act: -0.0001

Data Index: 28750 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2316. Min Act: -0.0001

Data Index: 1408664 (Python Code)

Max Activating Token Index: 813

Text #11

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2133. Min Act: -0.0001

Data Index: 20135 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2274. Min Act: -0.0001

Data Index: 1079646 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2244. Min Act: -0.0001

Data Index: 278093 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2534. Min Act: -0.0001

Data Index: 556848 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2437. Min Act: -0.0001

Data Index: 220818 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2350. Min Act: -0.0001

Data Index: 929221 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2257. Min Act: -0.0001

Data Index: 1013431 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2404. Min Act: -0.0001

Data Index: 161863 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2391. Min Act: -0.0001

Data Index: 1477559 (Python Code)

Max Activating Token Index: 877