Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1737 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.4650. Min Act: -0.1700

Data Index: 1637857 (Python Code)

Max Activating Token Index: 83

Text #1

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.4023. Min Act: -0.1700

Data Index: 1441226 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.4023. Min Act: -0.1700

Data Index: 1645887 (Python Code)

Max Activating Token Index: 953

Text #3

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.3395. Min Act: -0.1700

Data Index: 1544212 (Python Code)

Max Activating Token Index: 76

Text #4

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.3395. Min Act: -0.1699

Data Index: 1643145 (Python Code)

Max Activating Token Index: 16

Text #5

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.3081. Min Act: -0.1700

Data Index: 1545083 (Python Code)

Max Activating Token Index: 12

Text #6

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.2767. Min Act: -0.1700

Data Index: 1606399 (Python Code)

Max Activating Token Index: 97

Text #7

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.3081. Min Act: -0.1698

Data Index: 1434875 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.2767. Min Act: -0.1699

Data Index: 1453856 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.2767. Min Act: -0.1700

Data Index: 1544252 (Python Code)

Max Activating Token Index: 18

Text #10

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.2767. Min Act: -0.1699

Data Index: 1540739 (Python Code)

Max Activating Token Index: 442

Text #11

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.2767. Min Act: -0.1700

Data Index: 1579879 (Python Code)

Max Activating Token Index: 983

Text #12

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.2453. Min Act: -0.1700

Data Index: 1622043 (Python Code)

Max Activating Token Index: 378

Text #13

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.2453. Min Act: -0.1700

Data Index: 1417350 (Python Code)

Max Activating Token Index: 153

Text #14

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.2453. Min Act: -0.1700

Data Index: 1626330 (Python Code)

Max Activating Token Index: 136

Text #15

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.2453. Min Act: -0.1700

Data Index: 1418969 (Python Code)

Max Activating Token Index: 361

Text #16

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.2453. Min Act: -0.1700

Data Index: 1641239 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.2453. Min Act: -0.1700

Data Index: 1556470 (Python Code)

Max Activating Token Index: 453

Text #18

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.2138. Min Act: -0.1700

Data Index: 1361589 (Python Code)

Max Activating Token Index: 191

Text #19

Max Range: 3.4650. Min Range: -3.4650

Max Act: 3.2138. Min Act: -0.1700

Data Index: 1416380 (Python Code)

Max Activating Token Index: 5