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

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

Neuron 4065 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: 0.6285. Min Range: -0.6285

Max Act: 0.6142. Min Act: -0.0001

Data Index: 1044421 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.5943. Min Act: -0.0000

Data Index: 566156 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.6285. Min Act: -0.0000

Data Index: 358694 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.5925. Min Act: -0.0000

Data Index: 432740 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.5353. Min Act: -0.0001

Data Index: 717352 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.5526. Min Act: -0.0000

Data Index: 772235 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.5861. Min Act: -0.0001

Data Index: 1035549 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1349289 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.5406. Min Act: -0.0001

Data Index: 1598274 (Python Code)

Max Activating Token Index: 729

Text #9

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.5415. Min Act: -0.0001

Data Index: 825039 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1334814 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.5215. Min Act: -0.0001

Data Index: 425367 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.5303. Min Act: -0.0000

Data Index: 138192 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.5287. Min Act: -0.0000

Data Index: 113784 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.5257. Min Act: -0.0000

Data Index: 967767 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.5062. Min Act: -0.0001

Data Index: 1255096 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1065947 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.5163. Min Act: -0.0000

Data Index: 926682 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1120958 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.4782. Min Act: -0.0000

Data Index: 339693 (C4 (Web Text))

Max Activating Token Index: 976