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

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

Neuron 1803 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: 3.0055. Min Range: -3.0055

Max Act: 3.0055. Min Act: -0.1700

Data Index: 1384063 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.0055. Min Range: -3.0055

Max Act: 3.0055. Min Act: -0.1700

Data Index: 1497237 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.8629. Min Act: -0.1700

Data Index: 1563898 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.7674. Min Act: -0.1700

Data Index: 1609860 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.7195. Min Act: -0.1700

Data Index: 1493755 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.6233. Min Act: -0.1700

Data Index: 1584257 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.5911. Min Act: -0.1700

Data Index: 1405016 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.6072. Min Act: -0.1700

Data Index: 1486654 (Python Code)

Max Activating Token Index: 77

Text #8

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.5589. Min Act: -0.1700

Data Index: 1583050 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.5750. Min Act: -0.1700

Data Index: 1609702 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.5428. Min Act: -0.1700

Data Index: 1372393 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.5266. Min Act: -0.1700

Data Index: 1620350 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.4780. Min Act: -0.1700

Data Index: 1522622 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.4942. Min Act: -0.1700

Data Index: 1566956 (Python Code)

Max Activating Token Index: 287

Text #14

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.4780. Min Act: -0.1700

Data Index: 1410904 (Python Code)

Max Activating Token Index: 104

Text #15

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.4780. Min Act: -0.1700

Data Index: 1550724 (Python Code)

Max Activating Token Index: 798

Text #16

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.4780. Min Act: -0.1700

Data Index: 1597653 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.4780. Min Act: -0.1700

Data Index: 1472784 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.4780. Min Act: -0.1700

Data Index: 1474079 (Python Code)

Max Activating Token Index: 705

Text #19

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.4780. Min Act: -0.1700

Data Index: 1437232 (Python Code)

Max Activating Token Index: 1023