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

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

Neuron 514 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.6765. Min Act: -0.1700

Data Index: 523932 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.4265. Min Act: -0.1700

Data Index: 720726 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.4890. Min Act: -0.1700

Data Index: 501875 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.4890. Min Act: -0.1700

Data Index: 249551 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.3015. Min Act: -0.1700

Data Index: 456471 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.3328. Min Act: -0.1700

Data Index: 1260104 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.2703. Min Act: -0.1700

Data Index: 266137 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.3328. Min Act: -0.1700

Data Index: 1214753 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.3015. Min Act: -0.1700

Data Index: 374247 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.2703. Min Act: -0.1700

Data Index: 931860 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.2703. Min Act: -0.1700

Data Index: 210511 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.3015. Min Act: -0.1700

Data Index: 971029 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.2703. Min Act: -0.1700

Data Index: 778787 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.2390. Min Act: -0.1700

Data Index: 1300107 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.2390. Min Act: -0.1700

Data Index: 1205130 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.2390. Min Act: -0.1700

Data Index: 243174 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.2703. Min Act: -0.1700

Data Index: 888089 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.2078. Min Act: -0.1700

Data Index: 1305804 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.2390. Min Act: -0.1700

Data Index: 984108 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 5.6765. Min Range: -5.6765

Max Act: 5.2703. Min Act: -0.1700

Data Index: 125351 (C4 (Web Text))

Max Activating Token Index: 900