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

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

Neuron 3835 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.8260. Min Act: -0.0001

Data Index: 739497 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.5938. Min Act: -0.0002

Data Index: 1095948 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.5768. Min Act: -0.0002

Data Index: 350855 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.5194. Min Act: -0.0002

Data Index: 599857 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.4907. Min Act: -0.0002

Data Index: 894662 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.4854. Min Act: -0.0002

Data Index: 859130 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.5609. Min Act: -0.0002

Data Index: 879887 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.3108. Min Act: -0.0001

Data Index: 1142585 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.4573. Min Act: -0.0002

Data Index: 980981 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.3018. Min Act: -0.0002

Data Index: 1234120 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.3611. Min Act: -0.0002

Data Index: 1306945 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.3836. Min Act: -0.0001

Data Index: 2289 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.4515. Min Act: -0.0001

Data Index: 331856 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.3840. Min Act: -0.0001

Data Index: 384036 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.4302. Min Act: -0.0001

Data Index: 9112 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.3203. Min Act: -0.0002

Data Index: 20199 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.3979. Min Act: -0.0001

Data Index: 1281418 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.3046. Min Act: -0.0001

Data Index: 1330681 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.3078. Min Act: -0.0002

Data Index: 75240 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.1803. Min Act: -0.0002

Data Index: 1620994 (Python Code)

Max Activating Token Index: 572