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

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

Neuron 569 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: 3.8555. Min Range: -3.8555

Max Act: 3.8555. Min Act: -0.1700

Data Index: 1127325 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 3.8555. Min Range: -3.8555

Max Act: 3.8243. Min Act: -0.1700

Data Index: 1004055 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 3.8555. Min Range: -3.8555

Max Act: 3.8086. Min Act: -0.1700

Data Index: 500561 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 3.8555. Min Range: -3.8555

Max Act: 3.7304. Min Act: -0.1700

Data Index: 1039526 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 3.8555. Min Range: -3.8555

Max Act: 3.6991. Min Act: -0.1700

Data Index: 974834 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 3.8555. Min Range: -3.8555

Max Act: 3.6835. Min Act: -0.1700

Data Index: 151405 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 3.8555. Min Range: -3.8555

Max Act: 3.6678. Min Act: -0.1700

Data Index: 541183 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 3.8555. Min Range: -3.8555

Max Act: 3.6678. Min Act: -0.1700

Data Index: 174534 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 3.8555. Min Range: -3.8555

Max Act: 3.6835. Min Act: -0.1700

Data Index: 1046888 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 3.8555. Min Range: -3.8555

Max Act: 3.6365. Min Act: -0.1700

Data Index: 1504890 (Python Code)

Max Activating Token Index: 487

Text #10

Max Range: 3.8555. Min Range: -3.8555

Max Act: 3.6365. Min Act: -0.1700

Data Index: 882869 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 3.8555. Min Range: -3.8555

Max Act: 3.6209. Min Act: -0.1700

Data Index: 697577 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 3.8555. Min Range: -3.8555

Max Act: 3.6365. Min Act: -0.1700

Data Index: 1319177 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 3.8555. Min Range: -3.8555

Max Act: 3.6209. Min Act: -0.1700

Data Index: 695154 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 3.8555. Min Range: -3.8555

Max Act: 3.6365. Min Act: -0.1700

Data Index: 201656 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 3.8555. Min Range: -3.8555

Max Act: 3.6365. Min Act: -0.1700

Data Index: 918462 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 3.8555. Min Range: -3.8555

Max Act: 3.6365. Min Act: -0.1700

Data Index: 44051 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 3.8555. Min Range: -3.8555

Max Act: 3.6209. Min Act: -0.1699

Data Index: 258458 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 3.8555. Min Range: -3.8555

Max Act: 3.6052. Min Act: -0.1700

Data Index: 559956 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 3.8555. Min Range: -3.8555

Max Act: 3.6365. Min Act: -0.1700

Data Index: 191465 (C4 (Web Text))

Max Activating Token Index: 22