Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 660 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.8400. Min Act: -0.1700

Data Index: 1592762 (Python Code)

Max Activating Token Index: 73

Text #1

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.8400. Min Act: -0.1698

Data Index: 1432321 (Python Code)

Max Activating Token Index: 149

Text #2

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.8244. Min Act: -0.1700

Data Index: 1498090 (Python Code)

Max Activating Token Index: 550

Text #3

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.8400. Min Act: -0.1700

Data Index: 1594745 (Python Code)

Max Activating Token Index: 324

Text #4

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.8400. Min Act: -0.1700

Data Index: 740666 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.7931. Min Act: -0.1700

Data Index: 1595404 (Python Code)

Max Activating Token Index: 584

Text #6

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.7931. Min Act: -0.1700

Data Index: 1648083 (Python Code)

Max Activating Token Index: 69

Text #7

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.7931. Min Act: -0.1700

Data Index: 1511263 (Python Code)

Max Activating Token Index: 880

Text #8

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.7931. Min Act: -0.1700

Data Index: 1456093 (Python Code)

Max Activating Token Index: 872

Text #9

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.7149. Min Act: -0.1699

Data Index: 1637767 (Python Code)

Max Activating Token Index: 356

Text #10

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.7775. Min Act: -0.1699

Data Index: 1607147 (Python Code)

Max Activating Token Index: 753

Text #11

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.7149. Min Act: -0.1700

Data Index: 1631959 (Python Code)

Max Activating Token Index: 297

Text #12

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.7462. Min Act: -0.1700

Data Index: 1643090 (Python Code)

Max Activating Token Index: 576

Text #13

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.7305. Min Act: -0.1700

Data Index: 1535767 (Python Code)

Max Activating Token Index: 221

Text #14

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.7149. Min Act: -0.1700

Data Index: 1506496 (Python Code)

Max Activating Token Index: 685

Text #15

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.6992. Min Act: -0.1700

Data Index: 1506717 (Python Code)

Max Activating Token Index: 677

Text #16

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.6992. Min Act: -0.1700

Data Index: 1368795 (Python Code)

Max Activating Token Index: 259

Text #17

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.6992. Min Act: -0.1700

Data Index: 1496707 (Python Code)

Max Activating Token Index: 229

Text #18

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.6836. Min Act: -0.1700

Data Index: 1472972 (Python Code)

Max Activating Token Index: 928

Text #19

Max Range: 3.8400. Min Range: -3.8400

Max Act: 3.7149. Min Act: -0.1700

Data Index: 1478779 (Python Code)

Max Activating Token Index: 849