Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 888 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.7877. Min Act: -0.0000

Data Index: 562676 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.6849. Min Act: -0.0000

Data Index: 592573 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.6471. Min Act: -0.0000

Data Index: 423285 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.6015. Min Act: -0.0000

Data Index: 966784 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5985. Min Act: -0.0000

Data Index: 150227 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5731. Min Act: -0.0000

Data Index: 1029471 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5295. Min Act: -0.0000

Data Index: 93416 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5426. Min Act: -0.0000

Data Index: 169668 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5535. Min Act: -0.0000

Data Index: 591333 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1584311 (Python Code)

Max Activating Token Index: 958

Text #10

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.4955. Min Act: -0.0000

Data Index: 838462 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5181. Min Act: -0.0000

Data Index: 937012 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5204. Min Act: -0.0000

Data Index: 54613 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5142. Min Act: -0.0000

Data Index: 334113 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5455. Min Act: -0.0000

Data Index: 186983 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5073. Min Act: -0.0000

Data Index: 562567 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5499. Min Act: -0.0000

Data Index: 1206588 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.4880. Min Act: -0.0000

Data Index: 57285 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5106. Min Act: -0.0000

Data Index: 705222 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5093. Min Act: -0.0000

Data Index: 464178 (C4 (Web Text))

Max Activating Token Index: 743