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

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

Neuron 3409 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.7322. Min Act: -0.0001

Data Index: 1412296 (Python Code)

Max Activating Token Index: 91

Text #1

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.8876. Min Act: -0.0001

Data Index: 1387247 (Python Code)

Max Activating Token Index: 858

Text #2

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.7314. Min Act: -0.0001

Data Index: 1439508 (Python Code)

Max Activating Token Index: 939

Text #3

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.7163. Min Act: -0.0001

Data Index: 1519481 (Python Code)

Max Activating Token Index: 504

Text #4

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.7056. Min Act: -0.0001

Data Index: 1467957 (Python Code)

Max Activating Token Index: 463

Text #5

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.7866. Min Act: -0.0001

Data Index: 1561444 (Python Code)

Max Activating Token Index: 688

Text #6

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.6378. Min Act: -0.0001

Data Index: 1629259 (Python Code)

Max Activating Token Index: 540

Text #7

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.7181. Min Act: -0.0000

Data Index: 1570454 (Python Code)

Max Activating Token Index: 962

Text #8

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.6938. Min Act: -0.0001

Data Index: 1416835 (Python Code)

Max Activating Token Index: 979

Text #9

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.4988. Min Act: -0.0001

Data Index: 1587410 (Python Code)

Max Activating Token Index: 551

Text #10

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.5707. Min Act: -0.0001

Data Index: 1623159 (Python Code)

Max Activating Token Index: 186

Text #11

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.4899. Min Act: -0.0001

Data Index: 1580011 (Python Code)

Max Activating Token Index: 588

Text #12

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.4027. Min Act: -0.0001

Data Index: 1577007 (Python Code)

Max Activating Token Index: 524

Text #13

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.5041. Min Act: -0.0001

Data Index: 1387178 (Python Code)

Max Activating Token Index: 744

Text #14

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.4852. Min Act: -0.0000

Data Index: 1601949 (Python Code)

Max Activating Token Index: 165

Text #15

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.3967. Min Act: -0.0001

Data Index: 1476862 (Python Code)

Max Activating Token Index: 685

Text #16

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.4718. Min Act: -0.0001

Data Index: 1643759 (Python Code)

Max Activating Token Index: 405

Text #17

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.5179. Min Act: -0.0000

Data Index: 1587936 (Python Code)

Max Activating Token Index: 805

Text #18

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.4162. Min Act: -0.0000

Data Index: 1530939 (Python Code)

Max Activating Token Index: 801

Text #19

Max Range: 1.8876. Min Range: -1.8876

Max Act: 1.5260. Min Act: -0.0001

Data Index: 1384386 (Python Code)

Max Activating Token Index: 658