Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4458 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.3912. Min Act: -0.0000

Data Index: 1088107 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.2983. Min Act: -0.0000

Data Index: 1436249 (Python Code)

Max Activating Token Index: 747

Text #2

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.2947. Min Act: -0.0000

Data Index: 396080 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.2812. Min Act: -0.0000

Data Index: 763018 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.2324. Min Act: -0.0000

Data Index: 915992 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1183. Min Act: -0.0000

Data Index: 1483887 (Python Code)

Max Activating Token Index: 770

Text #6

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.0838. Min Act: -0.0000

Data Index: 528613 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1150. Min Act: -0.0000

Data Index: 453629 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1120. Min Act: -0.0000

Data Index: 1551152 (Python Code)

Max Activating Token Index: 993

Text #9

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1043. Min Act: -0.0000

Data Index: 509343 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1809. Min Act: -0.0000

Data Index: 332219 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1474939 (Python Code)

Max Activating Token Index: 45

Text #12

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1003. Min Act: -0.0000

Data Index: 1429939 (Python Code)

Max Activating Token Index: 460

Text #13

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.0111. Min Act: -0.0000

Data Index: 1450172 (Python Code)

Max Activating Token Index: 140

Text #14

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.0774. Min Act: -0.0000

Data Index: 1508273 (Python Code)

Max Activating Token Index: 518

Text #15

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.0727. Min Act: -0.0001

Data Index: 1551754 (Python Code)

Max Activating Token Index: 447

Text #16

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.0725. Min Act: -0.0001

Data Index: 1506123 (Python Code)

Max Activating Token Index: 807

Text #17

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.0633. Min Act: -0.0001

Data Index: 1426517 (Python Code)

Max Activating Token Index: 1009

Text #18

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.0585. Min Act: -0.0000

Data Index: 1626855 (Python Code)

Max Activating Token Index: 395

Text #19

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.0159. Min Act: -0.0001

Data Index: 491103 (C4 (Web Text))

Max Activating Token Index: 384