Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 275 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.3856. Min Act: -0.1700

Data Index: 45676 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.3228. Min Act: -0.1700

Data Index: 464765 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2757. Min Act: -0.1700

Data Index: 371742 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2914. Min Act: -0.1700

Data Index: 721758 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2757. Min Act: -0.1700

Data Index: 105518 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2600. Min Act: -0.1700

Data Index: 1246512 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2443. Min Act: -0.1700

Data Index: 720251 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2600. Min Act: -0.1700

Data Index: 978655 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2443. Min Act: -0.1700

Data Index: 1089960 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2128. Min Act: -0.1700

Data Index: 148885 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2443. Min Act: -0.1700

Data Index: 700158 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2128. Min Act: -0.1700

Data Index: 794412 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2128. Min Act: -0.1700

Data Index: 250830 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2128. Min Act: -0.1700

Data Index: 268820 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1971. Min Act: -0.1700

Data Index: 221980 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2128. Min Act: -0.1700

Data Index: 74731 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.2128. Min Act: -0.1700

Data Index: 1024470 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1971. Min Act: -0.1700

Data Index: 670590 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1971. Min Act: -0.1700

Data Index: 1086396 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 3.3856. Min Range: -3.3856

Max Act: 3.1656. Min Act: -0.1700

Data Index: 1184987 (C4 (Web Text))

Max Activating Token Index: 619