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

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

Neuron 1613 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1180. Min Range: -5.1180

Max Act: 5.1180. Min Act: -0.1700

Data Index: 1127708 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 5.1180. Min Range: -5.1180

Max Act: 5.0243. Min Act: -0.1700

Data Index: 321043 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 5.1180. Min Range: -5.1180

Max Act: 5.0243. Min Act: -0.1700

Data Index: 101382 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 5.1180. Min Range: -5.1180

Max Act: 5.0243. Min Act: -0.1700

Data Index: 234481 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 5.1180. Min Range: -5.1180

Max Act: 4.9930. Min Act: -0.1700

Data Index: 909519 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 5.1180. Min Range: -5.1180

Max Act: 5.0555. Min Act: -0.1700

Data Index: 1142864 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 5.1180. Min Range: -5.1180

Max Act: 4.9618. Min Act: -0.1700

Data Index: 1309968 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 5.1180. Min Range: -5.1180

Max Act: 4.9618. Min Act: -0.1700

Data Index: 851954 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 5.1180. Min Range: -5.1180

Max Act: 4.9305. Min Act: -0.1700

Data Index: 1101103 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 5.1180. Min Range: -5.1180

Max Act: 4.8993. Min Act: -0.1700

Data Index: 1076133 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 5.1180. Min Range: -5.1180

Max Act: 4.9618. Min Act: -0.1700

Data Index: 600478 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 5.1180. Min Range: -5.1180

Max Act: 4.9305. Min Act: -0.1700

Data Index: 491434 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 5.1180. Min Range: -5.1180

Max Act: 4.9305. Min Act: -0.1700

Data Index: 507761 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 5.1180. Min Range: -5.1180

Max Act: 4.9305. Min Act: -0.1700

Data Index: 235488 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 5.1180. Min Range: -5.1180

Max Act: 4.9618. Min Act: -0.1700

Data Index: 464723 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 5.1180. Min Range: -5.1180

Max Act: 4.9618. Min Act: -0.1700

Data Index: 1225327 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 5.1180. Min Range: -5.1180

Max Act: 4.9305. Min Act: -0.1700

Data Index: 1315566 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 5.1180. Min Range: -5.1180

Max Act: 4.8993. Min Act: -0.1700

Data Index: 640284 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 5.1180. Min Range: -5.1180

Max Act: 4.8680. Min Act: -0.1700

Data Index: 1199841 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 5.1180. Min Range: -5.1180

Max Act: 4.8993. Min Act: -0.1700

Data Index: 886275 (C4 (Web Text))

Max Activating Token Index: 117