Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 375 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.0612. Min Range: -3.0612

Max Act: 3.0612. Min Act: -0.1700

Data Index: 1349957 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9980. Min Act: -0.1700

Data Index: 1156800 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9980. Min Act: -0.1700

Data Index: 445424 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9506. Min Act: -0.1700

Data Index: 1304414 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9664. Min Act: -0.1700

Data Index: 829074 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9189. Min Act: -0.1700

Data Index: 207472 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9347. Min Act: -0.1700

Data Index: 13097 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9030. Min Act: -0.1700

Data Index: 522344 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9189. Min Act: -0.1700

Data Index: 1011786 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9030. Min Act: -0.1700

Data Index: 1212290 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9030. Min Act: -0.1700

Data Index: 655117 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9189. Min Act: -0.1700

Data Index: 850024 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9189. Min Act: -0.1700

Data Index: 1306310 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9030. Min Act: -0.1700

Data Index: 1030186 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9030. Min Act: -0.1700

Data Index: 371624 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.8713. Min Act: -0.1700

Data Index: 139583 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.9030. Min Act: -0.1700

Data Index: 736877 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.8872. Min Act: -0.1700

Data Index: 694501 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.8872. Min Act: -0.1700

Data Index: 1242732 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 3.0612. Min Range: -3.0612

Max Act: 2.8872. Min Act: -0.1700

Data Index: 1290566 (C4 (Web Text))

Max Activating Token Index: 513