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

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

Neuron 1271 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: 3.7341. Min Range: -3.7341

Max Act: 3.7341. Min Act: -0.1700

Data Index: 1393196 (Python Code)

Max Activating Token Index: 234

Text #1

Max Range: 3.7341. Min Range: -3.7341

Max Act: 3.6715. Min Act: -0.1700

Data Index: 1528545 (Python Code)

Max Activating Token Index: 1022

Text #2

Max Range: 3.7341. Min Range: -3.7341

Max Act: 3.6715. Min Act: -0.1700

Data Index: 1656596 (Python Code)

Max Activating Token Index: 48

Text #3

Max Range: 3.7341. Min Range: -3.7341

Max Act: 3.6089. Min Act: -0.1700

Data Index: 1642164 (Python Code)

Max Activating Token Index: 622

Text #4

Max Range: 3.7341. Min Range: -3.7341

Max Act: 3.6089. Min Act: -0.1700

Data Index: 1539479 (Python Code)

Max Activating Token Index: 764

Text #5

Max Range: 3.7341. Min Range: -3.7341

Max Act: 3.5149. Min Act: -0.1700

Data Index: 1435751 (Python Code)

Max Activating Token Index: 69

Text #6

Max Range: 3.7341. Min Range: -3.7341

Max Act: 3.5149. Min Act: -0.1700

Data Index: 1393706 (Python Code)

Max Activating Token Index: 552

Text #7

Max Range: 3.7341. Min Range: -3.7341

Max Act: 3.5463. Min Act: -0.1700

Data Index: 1450303 (Python Code)

Max Activating Token Index: 94

Text #8

Max Range: 3.7341. Min Range: -3.7341

Max Act: 3.5149. Min Act: -0.1700

Data Index: 1411597 (Python Code)

Max Activating Token Index: 819

Text #9

Max Range: 3.7341. Min Range: -3.7341

Max Act: 3.5463. Min Act: -0.1700

Data Index: 1535205 (Python Code)

Max Activating Token Index: 38

Text #10

Max Range: 3.7341. Min Range: -3.7341

Max Act: 3.4836. Min Act: -0.1700

Data Index: 1404313 (Python Code)

Max Activating Token Index: 532

Text #11

Max Range: 3.7341. Min Range: -3.7341

Max Act: 3.4522. Min Act: -0.1700

Data Index: 1612493 (Python Code)

Max Activating Token Index: 700

Text #12

Max Range: 3.7341. Min Range: -3.7341

Max Act: 3.4836. Min Act: -0.1700

Data Index: 1364761 (Python Code)

Max Activating Token Index: 188

Text #13

Max Range: 3.7341. Min Range: -3.7341

Max Act: 3.4209. Min Act: -0.1700

Data Index: 1604793 (Python Code)

Max Activating Token Index: 40

Text #14

Max Range: 3.7341. Min Range: -3.7341

Max Act: 3.4522. Min Act: -0.1700

Data Index: 1599036 (Python Code)

Max Activating Token Index: 686

Text #15

Max Range: 3.7341. Min Range: -3.7341

Max Act: 3.4522. Min Act: -0.1700

Data Index: 1482940 (Python Code)

Max Activating Token Index: 507

Text #16

Max Range: 3.7341. Min Range: -3.7341

Max Act: 3.3895. Min Act: -0.1700

Data Index: 1487209 (Python Code)

Max Activating Token Index: 646

Text #17

Max Range: 3.7341. Min Range: -3.7341

Max Act: 3.4522. Min Act: -0.1700

Data Index: 1604423 (Python Code)

Max Activating Token Index: 544

Text #18

Max Range: 3.7341. Min Range: -3.7341

Max Act: 3.4522. Min Act: -0.1700

Data Index: 1505933 (Python Code)

Max Activating Token Index: 870

Text #19

Max Range: 3.7341. Min Range: -3.7341

Max Act: 3.4522. Min Act: -0.1700

Data Index: 1424311 (Python Code)

Max Activating Token Index: 726