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

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

Neuron 1630 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.8899. Min Act: -0.0001

Data Index: 195063 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.8763. Min Act: -0.0001

Data Index: 1207355 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.8763. Min Act: -0.0001

Data Index: 541963 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.8763. Min Act: -0.0001

Data Index: 424622 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.8763. Min Act: -0.0001

Data Index: 732083 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.8763. Min Act: -0.0001

Data Index: 1049873 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.8763. Min Act: -0.0001

Data Index: 559730 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.8495. Min Act: -0.0001

Data Index: 1082360 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.8434. Min Act: -0.0001

Data Index: 1270570 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.8171. Min Act: -0.0001

Data Index: 817096 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.8462. Min Act: -0.0001

Data Index: 816270 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.7929. Min Act: -0.0001

Data Index: 1216984 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.7834. Min Act: -0.0001

Data Index: 1055805 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.7823. Min Act: -0.0001

Data Index: 170055 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.7393. Min Act: -0.0001

Data Index: 377856 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.7472. Min Act: -0.0001

Data Index: 251671 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.8492. Min Act: -0.0001

Data Index: 908665 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.7268. Min Act: -0.0001

Data Index: 1789 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.7183. Min Act: -0.0001

Data Index: 777430 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.8899. Min Range: -0.8899

Max Act: 0.7222. Min Act: -0.0001

Data Index: 264900 (C4 (Web Text))

Max Activating Token Index: 979