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

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

Neuron 1513 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: 0.5928. Min Range: -0.5928

Max Act: 0.5928. Min Act: -0.0001

Data Index: 1272642 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.5290. Min Act: -0.0001

Data Index: 717946 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.5154. Min Act: -0.0000

Data Index: 620651 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4856. Min Act: -0.0001

Data Index: 1537120 (Python Code)

Max Activating Token Index: 297

Text #4

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4814. Min Act: -0.0001

Data Index: 1060696 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4705. Min Act: -0.0000

Data Index: 1359180 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4532. Min Act: -0.0001

Data Index: 1266999 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4527. Min Act: -0.0001

Data Index: 1638343 (Python Code)

Max Activating Token Index: 439

Text #8

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4419. Min Act: -0.0001

Data Index: 1481963 (Python Code)

Max Activating Token Index: 171

Text #9

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4379. Min Act: -0.0000

Data Index: 564575 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4059. Min Act: -0.0000

Data Index: 93801 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4330. Min Act: -0.0001

Data Index: 1101923 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4303. Min Act: -0.0001

Data Index: 1547176 (Python Code)

Max Activating Token Index: 883

Text #13

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4170. Min Act: -0.0001

Data Index: 140185 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.3847. Min Act: -0.0001

Data Index: 1455063 (Python Code)

Max Activating Token Index: 177

Text #15

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.3962. Min Act: -0.0001

Data Index: 1412232 (Python Code)

Max Activating Token Index: 491

Text #16

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.3788. Min Act: -0.0001

Data Index: 1502521 (Python Code)

Max Activating Token Index: 99

Text #17

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.3908. Min Act: -0.0001

Data Index: 252230 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.3761. Min Act: -0.0001

Data Index: 1511919 (Python Code)

Max Activating Token Index: 475

Text #19

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.3771. Min Act: -0.0001

Data Index: 1421198 (Python Code)

Max Activating Token Index: 614