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

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

Neuron 1678 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6726. Min Act: -0.0001

Data Index: 664593 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6578. Min Act: -0.0001

Data Index: 753295 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6484. Min Act: -0.0001

Data Index: 780447 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6580. Min Act: -0.0001

Data Index: 1079254 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6461. Min Act: -0.0001

Data Index: 969107 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6434. Min Act: -0.0001

Data Index: 1139625 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6452. Min Act: -0.0001

Data Index: 342952 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6314. Min Act: -0.0001

Data Index: 626281 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6425. Min Act: -0.0001

Data Index: 1063675 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6243. Min Act: -0.0001

Data Index: 586828 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6209. Min Act: -0.0001

Data Index: 157211 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6259. Min Act: -0.0001

Data Index: 1221790 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6192. Min Act: -0.0001

Data Index: 1016093 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6071. Min Act: -0.0001

Data Index: 539275 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6117. Min Act: -0.0001

Data Index: 458341 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6204. Min Act: -0.0001

Data Index: 895836 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6134. Min Act: -0.0001

Data Index: 1276017 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6098. Min Act: -0.0001

Data Index: 1296333 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6136. Min Act: -0.0001

Data Index: 648769 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.6726. Min Range: -0.6726

Max Act: 0.6026. Min Act: -0.0001

Data Index: 563691 (C4 (Web Text))

Max Activating Token Index: 28