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

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

Neuron 1046 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.2261. Min Act: -0.1700

Data Index: 1478768 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.1946. Min Act: -0.1700

Data Index: 1005406 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.2103. Min Act: -0.1700

Data Index: 1435093 (Python Code)

Max Activating Token Index: 103

Text #3

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.1789. Min Act: -0.1700

Data Index: 1387921 (Python Code)

Max Activating Token Index: 761

Text #4

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.1789. Min Act: -0.1700

Data Index: 1387511 (Python Code)

Max Activating Token Index: 30

Text #5

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.1789. Min Act: -0.1700

Data Index: 1633844 (Python Code)

Max Activating Token Index: 20

Text #6

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.1631. Min Act: -0.1700

Data Index: 1602267 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.1631. Min Act: -0.1700

Data Index: 1461403 (Python Code)

Max Activating Token Index: 10

Text #8

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.1631. Min Act: -0.1700

Data Index: 1536317 (Python Code)

Max Activating Token Index: 26

Text #9

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.1631. Min Act: -0.1700

Data Index: 1429500 (Python Code)

Max Activating Token Index: 62

Text #10

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.1474. Min Act: -0.1700

Data Index: 1631538 (Python Code)

Max Activating Token Index: 254

Text #11

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.1316. Min Act: -0.1700

Data Index: 1400494 (Python Code)

Max Activating Token Index: 599

Text #12

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.1316. Min Act: -0.1700

Data Index: 1380325 (Python Code)

Max Activating Token Index: 831

Text #13

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.1316. Min Act: -0.1700

Data Index: 1465832 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.1316. Min Act: -0.1700

Data Index: 1481429 (Python Code)

Max Activating Token Index: 468

Text #15

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.1316. Min Act: -0.1700

Data Index: 1417157 (Python Code)

Max Activating Token Index: 102

Text #16

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.1316. Min Act: -0.1700

Data Index: 1449182 (Python Code)

Max Activating Token Index: 12

Text #17

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.1316. Min Act: -0.1700

Data Index: 1600289 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.1159. Min Act: -0.1700

Data Index: 1421036 (Python Code)

Max Activating Token Index: 581

Text #19

Max Range: 3.2261. Min Range: -3.2261

Max Act: 3.1159. Min Act: -0.1700

Data Index: 1447963 (Python Code)

Max Activating Token Index: 496