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

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

Neuron 2926 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.7969. Min Act: -0.0001

Data Index: 1500956 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5768. Min Act: -0.0001

Data Index: 1607739 (Python Code)

Max Activating Token Index: 902

Text #2

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5139. Min Act: -0.0001

Data Index: 118968 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4974. Min Act: -0.0001

Data Index: 406601 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5360. Min Act: -0.0001

Data Index: 1606693 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5350. Min Act: -0.0001

Data Index: 1557905 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5141. Min Act: -0.0001

Data Index: 1399540 (Python Code)

Max Activating Token Index: 481

Text #7

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5313. Min Act: -0.0001

Data Index: 1427239 (Python Code)

Max Activating Token Index: 67

Text #8

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5197. Min Act: -0.0001

Data Index: 1431486 (Python Code)

Max Activating Token Index: 308

Text #9

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5264. Min Act: -0.0001

Data Index: 1375618 (Python Code)

Max Activating Token Index: 192

Text #10

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4850. Min Act: -0.0001

Data Index: 1610728 (Python Code)

Max Activating Token Index: 467

Text #11

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4861. Min Act: -0.0001

Data Index: 1536246 (Python Code)

Max Activating Token Index: 822

Text #12

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5193. Min Act: -0.0001

Data Index: 1594173 (Python Code)

Max Activating Token Index: 214

Text #13

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4990. Min Act: -0.0001

Data Index: 1602007 (Python Code)

Max Activating Token Index: 324

Text #14

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4774. Min Act: -0.0001

Data Index: 1489752 (Python Code)

Max Activating Token Index: 419

Text #15

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4908. Min Act: -0.0001

Data Index: 1440754 (Python Code)

Max Activating Token Index: 511

Text #16

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4755. Min Act: -0.0001

Data Index: 1553323 (Python Code)

Max Activating Token Index: 335

Text #17

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5081. Min Act: -0.0001

Data Index: 1449875 (Python Code)

Max Activating Token Index: 226

Text #18

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5142. Min Act: -0.0001

Data Index: 1275955 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.4863. Min Act: -0.0001

Data Index: 1486876 (Python Code)

Max Activating Token Index: 308