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

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

Neuron 889 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: 3.5030. Min Range: -3.5030

Max Act: 3.5030. Min Act: -0.1700

Data Index: 1622053 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.5030. Min Range: -3.5030

Max Act: 3.2205. Min Act: -0.1699

Data Index: 1625659 (Python Code)

Max Activating Token Index: 56

Text #2

Max Range: 3.5030. Min Range: -3.5030

Max Act: 3.2048. Min Act: -0.1699

Data Index: 1619373 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.5030. Min Range: -3.5030

Max Act: 3.2048. Min Act: -0.1699

Data Index: 1516568 (Python Code)

Max Activating Token Index: 433

Text #4

Max Range: 3.5030. Min Range: -3.5030

Max Act: 3.1576. Min Act: -0.1700

Data Index: 1522503 (Python Code)

Max Activating Token Index: 701

Text #5

Max Range: 3.5030. Min Range: -3.5030

Max Act: 3.1418. Min Act: -0.1700

Data Index: 1372615 (Python Code)

Max Activating Token Index: 142

Text #6

Max Range: 3.5030. Min Range: -3.5030

Max Act: 3.1261. Min Act: -0.1700

Data Index: 1511978 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.5030. Min Range: -3.5030

Max Act: 3.0946. Min Act: -0.1700

Data Index: 1392341 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 3.5030. Min Range: -3.5030

Max Act: 3.0788. Min Act: -0.1700

Data Index: 1587435 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.5030. Min Range: -3.5030

Max Act: 3.0788. Min Act: -0.1700

Data Index: 1637440 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 3.5030. Min Range: -3.5030

Max Act: 3.0630. Min Act: -0.1700

Data Index: 1551968 (Python Code)

Max Activating Token Index: 261

Text #11

Max Range: 3.5030. Min Range: -3.5030

Max Act: 3.0472. Min Act: -0.1700

Data Index: 1368520 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 3.5030. Min Range: -3.5030

Max Act: 3.0472. Min Act: -0.1700

Data Index: 1365354 (Python Code)

Max Activating Token Index: 685

Text #13

Max Range: 3.5030. Min Range: -3.5030

Max Act: 3.0472. Min Act: -0.1688

Data Index: 1361182 (Python Code)

Max Activating Token Index: 406

Text #14

Max Range: 3.5030. Min Range: -3.5030

Max Act: 3.0472. Min Act: -0.1700

Data Index: 1552635 (Python Code)

Max Activating Token Index: 676

Text #15

Max Range: 3.5030. Min Range: -3.5030

Max Act: 3.0472. Min Act: -0.1700

Data Index: 1521134 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 3.5030. Min Range: -3.5030

Max Act: 3.0314. Min Act: -0.1700

Data Index: 1409955 (Python Code)

Max Activating Token Index: 957

Text #17

Max Range: 3.5030. Min Range: -3.5030

Max Act: 3.0314. Min Act: -0.1700

Data Index: 1615021 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 3.5030. Min Range: -3.5030

Max Act: 3.0314. Min Act: -0.1700

Data Index: 1507350 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 3.5030. Min Range: -3.5030

Max Act: 3.0314. Min Act: -0.1700

Data Index: 1608090 (Python Code)

Max Activating Token Index: 963