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

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

Neuron 3209 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.3068. Min Act: -0.0001

Data Index: 1497596 (Python Code)

Max Activating Token Index: 457

Text #1

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2666. Min Act: -0.0001

Data Index: 685004 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2628. Min Act: -0.0001

Data Index: 537464 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2355. Min Act: -0.0001

Data Index: 1449453 (Python Code)

Max Activating Token Index: 112

Text #4

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2472. Min Act: -0.0001

Data Index: 1378894 (Python Code)

Max Activating Token Index: 485

Text #5

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2403. Min Act: -0.0001

Data Index: 1390376 (Python Code)

Max Activating Token Index: 274

Text #6

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2451. Min Act: -0.0000

Data Index: 57263 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2294. Min Act: -0.0000

Data Index: 1205027 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2214. Min Act: -0.0001

Data Index: 284699 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2182. Min Act: -0.0001

Data Index: 1629908 (Python Code)

Max Activating Token Index: 409

Text #10

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2032. Min Act: -0.0001

Data Index: 268796 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2101. Min Act: -0.0001

Data Index: 1432472 (Python Code)

Max Activating Token Index: 214

Text #12

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2152. Min Act: -0.0001

Data Index: 1512194 (Python Code)

Max Activating Token Index: 188

Text #13

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2135. Min Act: -0.0001

Data Index: 978979 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2258. Min Act: -0.0001

Data Index: 1487634 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2159. Min Act: -0.0000

Data Index: 123542 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.1936. Min Act: -0.0001

Data Index: 1062527 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2068. Min Act: -0.0000

Data Index: 105182 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2064. Min Act: -0.0001

Data Index: 1535489 (Python Code)

Max Activating Token Index: 636

Text #19

Max Range: 0.3068. Min Range: -0.3068

Max Act: 0.2295. Min Act: -0.0000

Data Index: 565834 (C4 (Web Text))

Max Activating Token Index: 750