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

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

Neuron 331 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3172. Min Range: -7.3172

Max Act: 7.3172. Min Act: -0.1700

Data Index: 1455908 (Python Code)

Max Activating Token Index: 806

Text #1

Max Range: 7.3172. Min Range: -7.3172

Max Act: 7.2860. Min Act: -0.1700

Data Index: 1528629 (Python Code)

Max Activating Token Index: 36

Text #2

Max Range: 7.3172. Min Range: -7.3172

Max Act: 7.2547. Min Act: -0.1700

Data Index: 1454669 (Python Code)

Max Activating Token Index: 107

Text #3

Max Range: 7.3172. Min Range: -7.3172

Max Act: 7.2547. Min Act: -0.1700

Data Index: 1376913 (Python Code)

Max Activating Token Index: 36

Text #4

Max Range: 7.3172. Min Range: -7.3172

Max Act: 7.1297. Min Act: -0.1700

Data Index: 1463625 (Python Code)

Max Activating Token Index: 44

Text #5

Max Range: 7.3172. Min Range: -7.3172

Max Act: 7.0672. Min Act: -0.1700

Data Index: 1477600 (Python Code)

Max Activating Token Index: 735

Text #6

Max Range: 7.3172. Min Range: -7.3172

Max Act: 6.9422. Min Act: -0.1700

Data Index: 1493428 (Python Code)

Max Activating Token Index: 202

Text #7

Max Range: 7.3172. Min Range: -7.3172

Max Act: 6.9735. Min Act: -0.1700

Data Index: 1502482 (Python Code)

Max Activating Token Index: 724

Text #8

Max Range: 7.3172. Min Range: -7.3172

Max Act: 6.9735. Min Act: -0.1700

Data Index: 1646516 (Python Code)

Max Activating Token Index: 114

Text #9

Max Range: 7.3172. Min Range: -7.3172

Max Act: 6.9110. Min Act: -0.1700

Data Index: 1441340 (Python Code)

Max Activating Token Index: 414

Text #10

Max Range: 7.3172. Min Range: -7.3172

Max Act: 6.8797. Min Act: -0.1700

Data Index: 1396907 (Python Code)

Max Activating Token Index: 128

Text #11

Max Range: 7.3172. Min Range: -7.3172

Max Act: 6.8485. Min Act: -0.1700

Data Index: 1453884 (Python Code)

Max Activating Token Index: 858

Text #12

Max Range: 7.3172. Min Range: -7.3172

Max Act: 6.9422. Min Act: -0.1700

Data Index: 1373144 (Python Code)

Max Activating Token Index: 92

Text #13

Max Range: 7.3172. Min Range: -7.3172

Max Act: 6.8485. Min Act: -0.1700

Data Index: 1613842 (Python Code)

Max Activating Token Index: 614

Text #14

Max Range: 7.3172. Min Range: -7.3172

Max Act: 6.9422. Min Act: -0.1700

Data Index: 1382163 (Python Code)

Max Activating Token Index: 523

Text #15

Max Range: 7.3172. Min Range: -7.3172

Max Act: 6.8485. Min Act: -0.1700

Data Index: 1486131 (Python Code)

Max Activating Token Index: 634

Text #16

Max Range: 7.3172. Min Range: -7.3172

Max Act: 6.7547. Min Act: -0.1700

Data Index: 1453057 (Python Code)

Max Activating Token Index: 773

Text #17

Max Range: 7.3172. Min Range: -7.3172

Max Act: 6.7235. Min Act: -0.1700

Data Index: 1400469 (Python Code)

Max Activating Token Index: 1018

Text #18

Max Range: 7.3172. Min Range: -7.3172

Max Act: 6.8172. Min Act: -0.1700

Data Index: 1545899 (Python Code)

Max Activating Token Index: 701

Text #19

Max Range: 7.3172. Min Range: -7.3172

Max Act: 6.7860. Min Act: -0.1700

Data Index: 1482552 (Python Code)

Max Activating Token Index: 86