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

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

Neuron 1778 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.8581. Min Act: -0.1700

Data Index: 1069257 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.6391. Min Act: -0.1698

Data Index: 1222738 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.6078. Min Act: -0.1691

Data Index: 1123020 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.6078. Min Act: -0.1700

Data Index: 1275606 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.5451. Min Act: -0.1700

Data Index: 392986 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.5764. Min Act: -0.1700

Data Index: 888628 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.4825. Min Act: -0.1700

Data Index: 50569 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.4511. Min Act: -0.1700

Data Index: 1288224 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.4511. Min Act: -0.1699

Data Index: 845842 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.4197. Min Act: -0.1700

Data Index: 409843 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.4197. Min Act: -0.1700

Data Index: 435260 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.4825. Min Act: -0.1700

Data Index: 439533 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.4511. Min Act: -0.1700

Data Index: 665345 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.4511. Min Act: -0.1700

Data Index: 1271713 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.4511. Min Act: -0.1700

Data Index: 802334 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.4511. Min Act: -0.1700

Data Index: 450839 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.4197. Min Act: -0.1700

Data Index: 56152 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.4197. Min Act: -0.1699

Data Index: 503528 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.3884. Min Act: -0.1700

Data Index: 1087843 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 3.8581. Min Range: -3.8581

Max Act: 3.3884. Min Act: -0.1700

Data Index: 109825 (C4 (Web Text))

Max Activating Token Index: 431