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

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

Neuron 1001 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1575225 (Python Code)

Max Activating Token Index: 3

Text #1

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1430646 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1634976 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1520398 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1621503 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1591945 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1373069 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1580640 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1487429 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1578894 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1422534 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1554331 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1545629 (Python Code)

Max Activating Token Index: 3

Text #13

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1542529 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1447972 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1653514 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1539726 (Python Code)

Max Activating Token Index: 3

Text #17

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6086. Min Act: -0.1700

Data Index: 1431412 (Python Code)

Max Activating Token Index: 2

Text #18

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.5460. Min Act: -0.1700

Data Index: 1637967 (Python Code)

Max Activating Token Index: 4

Text #19

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.5147. Min Act: -0.1700

Data Index: 1544790 (Python Code)

Max Activating Token Index: 2