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

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

Neuron 771 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: 5.5125. Min Range: -5.5125

Max Act: 5.5125. Min Act: -0.1700

Data Index: 1513571 (Python Code)

Max Activating Token Index: 861

Text #1

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.4500. Min Act: -0.1700

Data Index: 1551023 (Python Code)

Max Activating Token Index: 582

Text #2

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.3875. Min Act: -0.1700

Data Index: 1440774 (Python Code)

Max Activating Token Index: 963

Text #3

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.4500. Min Act: -0.1700

Data Index: 1527964 (Python Code)

Max Activating Token Index: 475

Text #4

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.3250. Min Act: -0.1700

Data Index: 1486245 (Python Code)

Max Activating Token Index: 977

Text #5

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.3562. Min Act: -0.1700

Data Index: 1473236 (Python Code)

Max Activating Token Index: 313

Text #6

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.3562. Min Act: -0.1700

Data Index: 1419263 (Python Code)

Max Activating Token Index: 133

Text #7

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.2937. Min Act: -0.1700

Data Index: 1523664 (Python Code)

Max Activating Token Index: 655

Text #8

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.2937. Min Act: -0.1700

Data Index: 1385076 (Python Code)

Max Activating Token Index: 175

Text #9

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.2625. Min Act: -0.1700

Data Index: 1414107 (Python Code)

Max Activating Token Index: 550

Text #10

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.2625. Min Act: -0.1700

Data Index: 1600690 (Python Code)

Max Activating Token Index: 239

Text #11

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.2000. Min Act: -0.1700

Data Index: 1448577 (Python Code)

Max Activating Token Index: 963

Text #12

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.2625. Min Act: -0.1700

Data Index: 1428670 (Python Code)

Max Activating Token Index: 463

Text #13

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.2000. Min Act: -0.1700

Data Index: 1548550 (Python Code)

Max Activating Token Index: 640

Text #14

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.2625. Min Act: -0.1700

Data Index: 1368816 (Python Code)

Max Activating Token Index: 243

Text #15

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.2000. Min Act: -0.1700

Data Index: 1502635 (Python Code)

Max Activating Token Index: 925

Text #16

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.2312. Min Act: -0.1700

Data Index: 1523224 (Python Code)

Max Activating Token Index: 104

Text #17

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.2625. Min Act: -0.1700

Data Index: 1520978 (Python Code)

Max Activating Token Index: 355

Text #18

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.2312. Min Act: -0.1700

Data Index: 1364678 (Python Code)

Max Activating Token Index: 60

Text #19

Max Range: 5.5125. Min Range: -5.5125

Max Act: 5.2312. Min Act: -0.1700

Data Index: 1527484 (Python Code)

Max Activating Token Index: 540