Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1687 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.3226. Min Act: -0.1700

Data Index: 71380 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.4324. Min Act: -0.1700

Data Index: 1156134 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.4481. Min Act: -0.1700

Data Index: 31783 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.3697. Min Act: -0.1700

Data Index: 1006799 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.3540. Min Act: -0.1700

Data Index: 516830 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.3383. Min Act: -0.1700

Data Index: 45205 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.3697. Min Act: -0.1700

Data Index: 298498 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.3540. Min Act: -0.1700

Data Index: 941380 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.3069. Min Act: -0.1700

Data Index: 781956 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.3069. Min Act: -0.1700

Data Index: 173891 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.2912. Min Act: -0.1700

Data Index: 257187 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.2912. Min Act: -0.1700

Data Index: 80106 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.2440. Min Act: -0.1700

Data Index: 382164 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.2283. Min Act: -0.1700

Data Index: 732171 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.2755. Min Act: -0.1700

Data Index: 436502 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.2283. Min Act: -0.1700

Data Index: 1176580 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.2283. Min Act: -0.1700

Data Index: 1204408 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.2283. Min Act: -0.1700

Data Index: 584627 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.2440. Min Act: -0.1700

Data Index: 398735 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.2283. Min Act: -0.1700

Data Index: 730095 (C4 (Web Text))

Max Activating Token Index: 318