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

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

Neuron 1434 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: 5.9153. Min Range: -5.9153

Max Act: 5.9153. Min Act: -0.1700

Data Index: 1246350 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 5.9153. Min Range: -5.9153

Max Act: 5.6653. Min Act: -0.1700

Data Index: 1061618 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 5.9153. Min Range: -5.9153

Max Act: 5.5715. Min Act: -0.1700

Data Index: 1281895 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 5.9153. Min Range: -5.9153

Max Act: 5.6028. Min Act: -0.1700

Data Index: 579573 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 5.9153. Min Range: -5.9153

Max Act: 5.5715. Min Act: -0.1700

Data Index: 277425 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 5.9153. Min Range: -5.9153

Max Act: 5.5403. Min Act: -0.1700

Data Index: 506048 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 5.9153. Min Range: -5.9153

Max Act: 5.5715. Min Act: -0.1700

Data Index: 105970 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 5.9153. Min Range: -5.9153

Max Act: 5.5403. Min Act: -0.1700

Data Index: 302720 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 5.9153. Min Range: -5.9153

Max Act: 5.4778. Min Act: -0.1700

Data Index: 830246 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 5.9153. Min Range: -5.9153

Max Act: 5.5090. Min Act: -0.1700

Data Index: 712233 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 5.9153. Min Range: -5.9153

Max Act: 5.5403. Min Act: -0.1700

Data Index: 487123 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 5.9153. Min Range: -5.9153

Max Act: 5.4778. Min Act: -0.1700

Data Index: 1026705 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 5.9153. Min Range: -5.9153

Max Act: 5.4778. Min Act: -0.1700

Data Index: 889427 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 5.9153. Min Range: -5.9153

Max Act: 5.4153. Min Act: -0.1700

Data Index: 281718 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 5.9153. Min Range: -5.9153

Max Act: 5.3840. Min Act: -0.1700

Data Index: 935721 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 5.9153. Min Range: -5.9153

Max Act: 5.3840. Min Act: -0.1700

Data Index: 1084480 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 5.9153. Min Range: -5.9153

Max Act: 5.3840. Min Act: -0.1700

Data Index: 757598 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 5.9153. Min Range: -5.9153

Max Act: 5.4153. Min Act: -0.1700

Data Index: 1272889 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 5.9153. Min Range: -5.9153

Max Act: 5.3840. Min Act: -0.1700

Data Index: 622907 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 5.9153. Min Range: -5.9153

Max Act: 5.3528. Min Act: -0.1700

Data Index: 374316 (C4 (Web Text))

Max Activating Token Index: 401