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

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

Neuron 2525 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: 0.2395. Min Range: -0.2395

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1023109 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2395. Min Act: -0.0000

Data Index: 1263329 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2345. Min Act: -0.0000

Data Index: 227233 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2259. Min Act: -0.0001

Data Index: 1510537 (Python Code)

Max Activating Token Index: 660

Text #4

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2144. Min Act: -0.0000

Data Index: 1066861 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2301. Min Act: -0.0001

Data Index: 1621261 (Python Code)

Max Activating Token Index: 684

Text #6

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2154. Min Act: -0.0001

Data Index: 1521358 (Python Code)

Max Activating Token Index: 562

Text #7

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2137. Min Act: -0.0001

Data Index: 423714 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2185. Min Act: -0.0000

Data Index: 727562 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2154. Min Act: -0.0001

Data Index: 1595906 (Python Code)

Max Activating Token Index: 804

Text #10

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2037. Min Act: -0.0001

Data Index: 1545524 (Python Code)

Max Activating Token Index: 262

Text #11

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2082. Min Act: -0.0000

Data Index: 140398 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2002. Min Act: -0.0000

Data Index: 537653 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2003. Min Act: -0.0001

Data Index: 420884 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2168. Min Act: -0.0001

Data Index: 1577781 (Python Code)

Max Activating Token Index: 828

Text #15

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2121. Min Act: -0.0000

Data Index: 836710 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2046. Min Act: -0.0000

Data Index: 52130 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1955. Min Act: -0.0000

Data Index: 1107360 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2091. Min Act: -0.0001

Data Index: 1491086 (Python Code)

Max Activating Token Index: 593

Text #19

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2025. Min Act: -0.0000

Data Index: 61647 (C4 (Web Text))

Max Activating Token Index: 15