Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1148 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.2566. Min Act: -0.1700

Data Index: 1609998 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.2095. Min Act: -0.1700

Data Index: 1544108 (Python Code)

Max Activating Token Index: 959

Text #2

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.1780. Min Act: -0.1700

Data Index: 1442090 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.1623. Min Act: -0.1700

Data Index: 1571702 (Python Code)

Max Activating Token Index: 182

Text #4

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.1465. Min Act: -0.1700

Data Index: 1571882 (Python Code)

Max Activating Token Index: 919

Text #5

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.1150. Min Act: -0.1700

Data Index: 1445228 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.1308. Min Act: -0.1700

Data Index: 1650898 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.1150. Min Act: -0.1700

Data Index: 1499772 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.1308. Min Act: -0.1700

Data Index: 1398253 (Python Code)

Max Activating Token Index: 181

Text #9

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.0992. Min Act: -0.1700

Data Index: 1592144 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.0992. Min Act: -0.1700

Data Index: 1536664 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.1308. Min Act: -0.1700

Data Index: 1365279 (Python Code)

Max Activating Token Index: 927

Text #12

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.0835. Min Act: -0.1700

Data Index: 1366882 (Python Code)

Max Activating Token Index: 981

Text #13

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.0992. Min Act: -0.1700

Data Index: 1476871 (Python Code)

Max Activating Token Index: 65

Text #14

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.0992. Min Act: -0.1700

Data Index: 1416880 (Python Code)

Max Activating Token Index: 852

Text #15

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.0835. Min Act: -0.1700

Data Index: 1529522 (Python Code)

Max Activating Token Index: 150

Text #16

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.0992. Min Act: -0.1700

Data Index: 1520998 (Python Code)

Max Activating Token Index: 13

Text #17

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.0677. Min Act: -0.1700

Data Index: 1402147 (Python Code)

Max Activating Token Index: 306

Text #18

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.0835. Min Act: -0.1700

Data Index: 1464369 (Python Code)

Max Activating Token Index: 322

Text #19

Max Range: 3.2566. Min Range: -3.2566

Max Act: 3.0677. Min Act: -0.1700

Data Index: 1373029 (Python Code)

Max Activating Token Index: 643