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

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

Neuron 979 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: 5.2982. Min Range: -5.2982

Max Act: 5.2982. Min Act: -0.1700

Data Index: 1629891 (Python Code)

Max Activating Token Index: 611

Text #1

Max Range: 5.2982. Min Range: -5.2982

Max Act: 5.1107. Min Act: -0.1700

Data Index: 1381387 (Python Code)

Max Activating Token Index: 289

Text #2

Max Range: 5.2982. Min Range: -5.2982

Max Act: 5.0795. Min Act: -0.1700

Data Index: 1474066 (Python Code)

Max Activating Token Index: 520

Text #3

Max Range: 5.2982. Min Range: -5.2982

Max Act: 5.0795. Min Act: -0.1700

Data Index: 1618433 (Python Code)

Max Activating Token Index: 513

Text #4

Max Range: 5.2982. Min Range: -5.2982

Max Act: 5.0482. Min Act: -0.1700

Data Index: 1593813 (Python Code)

Max Activating Token Index: 45

Text #5

Max Range: 5.2982. Min Range: -5.2982

Max Act: 5.0170. Min Act: -0.1700

Data Index: 1394387 (Python Code)

Max Activating Token Index: 798

Text #6

Max Range: 5.2982. Min Range: -5.2982

Max Act: 4.9857. Min Act: -0.1700

Data Index: 1376271 (Python Code)

Max Activating Token Index: 391

Text #7

Max Range: 5.2982. Min Range: -5.2982

Max Act: 4.9232. Min Act: -0.1700

Data Index: 1519647 (Python Code)

Max Activating Token Index: 752

Text #8

Max Range: 5.2982. Min Range: -5.2982

Max Act: 4.8920. Min Act: -0.1700

Data Index: 1398966 (Python Code)

Max Activating Token Index: 160

Text #9

Max Range: 5.2982. Min Range: -5.2982

Max Act: 4.9545. Min Act: -0.1700

Data Index: 1652329 (Python Code)

Max Activating Token Index: 277

Text #10

Max Range: 5.2982. Min Range: -5.2982

Max Act: 4.8920. Min Act: -0.1700

Data Index: 1504385 (Python Code)

Max Activating Token Index: 385

Text #11

Max Range: 5.2982. Min Range: -5.2982

Max Act: 4.9232. Min Act: -0.1700

Data Index: 1546039 (Python Code)

Max Activating Token Index: 783

Text #12

Max Range: 5.2982. Min Range: -5.2982

Max Act: 4.8920. Min Act: -0.1700

Data Index: 1641743 (Python Code)

Max Activating Token Index: 727

Text #13

Max Range: 5.2982. Min Range: -5.2982

Max Act: 4.9232. Min Act: -0.1700

Data Index: 1436620 (Python Code)

Max Activating Token Index: 281

Text #14

Max Range: 5.2982. Min Range: -5.2982

Max Act: 4.9545. Min Act: -0.1700

Data Index: 1549440 (Python Code)

Max Activating Token Index: 121

Text #15

Max Range: 5.2982. Min Range: -5.2982

Max Act: 4.8920. Min Act: -0.1700

Data Index: 1552001 (Python Code)

Max Activating Token Index: 196

Text #16

Max Range: 5.2982. Min Range: -5.2982

Max Act: 4.8920. Min Act: -0.1700

Data Index: 1363744 (Python Code)

Max Activating Token Index: 205

Text #17

Max Range: 5.2982. Min Range: -5.2982

Max Act: 4.9232. Min Act: -0.1700

Data Index: 1382170 (Python Code)

Max Activating Token Index: 504

Text #18

Max Range: 5.2982. Min Range: -5.2982

Max Act: 4.9232. Min Act: -0.1700

Data Index: 1466090 (Python Code)

Max Activating Token Index: 522

Text #19

Max Range: 5.2982. Min Range: -5.2982

Max Act: 4.8607. Min Act: -0.1700

Data Index: 1498778 (Python Code)

Max Activating Token Index: 455