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

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

Neuron 1472 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.6808. Min Act: -0.1700

Data Index: 253408 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.6808. Min Act: -0.1700

Data Index: 1277565 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.6495. Min Act: -0.1700

Data Index: 303283 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.6181. Min Act: -0.1700

Data Index: 935128 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.6181. Min Act: -0.1700

Data Index: 206973 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.5868. Min Act: -0.1700

Data Index: 1119242 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.5868. Min Act: -0.1700

Data Index: 1146125 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.5868. Min Act: -0.1700

Data Index: 352271 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.5242. Min Act: -0.1700

Data Index: 857431 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.5555. Min Act: -0.1700

Data Index: 191524 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.5555. Min Act: -0.1700

Data Index: 1344654 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.6181. Min Act: -0.1700

Data Index: 353490 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.5868. Min Act: -0.1700

Data Index: 814306 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.5555. Min Act: -0.1700

Data Index: 108326 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.5555. Min Act: -0.1700

Data Index: 879534 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.5555. Min Act: -0.1700

Data Index: 519840 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.5242. Min Act: -0.1700

Data Index: 723648 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.4929. Min Act: -0.1700

Data Index: 411475 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.5555. Min Act: -0.1700

Data Index: 272041 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 3.6808. Min Range: -3.6808

Max Act: 3.5242. Min Act: -0.1700

Data Index: 743638 (C4 (Web Text))

Max Activating Token Index: 886