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

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

Neuron 1418 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: 3.1477. Min Range: -3.1477

Max Act: 3.1477. Min Act: -0.1700

Data Index: 1134091 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.1161. Min Act: -0.1700

Data Index: 1089771 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.1161. Min Act: -0.1700

Data Index: 1265684 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.1004. Min Act: -0.1700

Data Index: 1339133 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.1004. Min Act: -0.1700

Data Index: 1205333 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0688. Min Act: -0.1700

Data Index: 924930 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0846. Min Act: -0.1700

Data Index: 1315221 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0846. Min Act: -0.1700

Data Index: 521548 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0846. Min Act: -0.1700

Data Index: 254852 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0688. Min Act: -0.1700

Data Index: 114681 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 3.1477. Min Range: -3.1477

Max Act: 3.0373. Min Act: -0.1700

Data Index: 875073 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 3.1477. Min Range: -3.1477

Max Act: 2.9898. Min Act: -0.1700

Data Index: 387681 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 3.1477. Min Range: -3.1477

Max Act: 2.9898. Min Act: -0.1700

Data Index: 249351 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 3.1477. Min Range: -3.1477

Max Act: 2.9898. Min Act: -0.1700

Data Index: 255319 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 3.1477. Min Range: -3.1477

Max Act: 2.9582. Min Act: -0.1700

Data Index: 1543091 (Python Code)

Max Activating Token Index: 305

Text #15

Max Range: 3.1477. Min Range: -3.1477

Max Act: 2.9740. Min Act: -0.1700

Data Index: 40597 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 3.1477. Min Range: -3.1477

Max Act: 2.9582. Min Act: -0.1700

Data Index: 459811 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 3.1477. Min Range: -3.1477

Max Act: 2.9740. Min Act: -0.1700

Data Index: 595945 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 3.1477. Min Range: -3.1477

Max Act: 2.9582. Min Act: -0.1700

Data Index: 1340869 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 3.1477. Min Range: -3.1477

Max Act: 2.9582. Min Act: -0.1700

Data Index: 1275510 (C4 (Web Text))

Max Activating Token Index: 64