Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1979 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.9726. Min Act: -0.1700

Data Index: 1621174 (Python Code)

Max Activating Token Index: 183

Text #1

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.9569. Min Act: -0.1700

Data Index: 1457685 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.8788. Min Act: -0.1700

Data Index: 1637954 (Python Code)

Max Activating Token Index: 574

Text #3

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.9101. Min Act: -0.1700

Data Index: 1448038 (Python Code)

Max Activating Token Index: 49

Text #4

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.8476. Min Act: -0.1700

Data Index: 1415477 (Python Code)

Max Activating Token Index: 481

Text #5

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.8319. Min Act: -0.1700

Data Index: 1415347 (Python Code)

Max Activating Token Index: 628

Text #6

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.8319. Min Act: -0.1700

Data Index: 1441992 (Python Code)

Max Activating Token Index: 23

Text #7

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.7538. Min Act: -0.1700

Data Index: 1638031 (Python Code)

Max Activating Token Index: 489

Text #8

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.8319. Min Act: -0.1700

Data Index: 1404333 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.8163. Min Act: -0.1700

Data Index: 1652177 (Python Code)

Max Activating Token Index: 9

Text #10

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.7851. Min Act: -0.1700

Data Index: 1436299 (Python Code)

Max Activating Token Index: 21

Text #11

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.8007. Min Act: -0.1700

Data Index: 1404277 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.7851. Min Act: -0.1700

Data Index: 1611429 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.7382. Min Act: -0.1699

Data Index: 1438806 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.7382. Min Act: -0.1700

Data Index: 1367063 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.7382. Min Act: -0.1700

Data Index: 1569552 (Python Code)

Max Activating Token Index: 569

Text #16

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.7226. Min Act: -0.1700

Data Index: 1605269 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.7382. Min Act: -0.1700

Data Index: 1421673 (Python Code)

Max Activating Token Index: 20

Text #18

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.7069. Min Act: -0.1700

Data Index: 1546848 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 5.9726. Min Range: -5.9726

Max Act: 5.6757. Min Act: -0.1700

Data Index: 1401160 (Python Code)

Max Activating Token Index: 116