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

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

Neuron 1199 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6557. Min Range: -5.6557

Max Act: 5.6557. Min Act: -0.1700

Data Index: 1344704 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 5.6557. Min Range: -5.6557

Max Act: 5.4994. Min Act: -0.1700

Data Index: 729139 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 5.6557. Min Range: -5.6557

Max Act: 5.3432. Min Act: -0.1700

Data Index: 666896 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 5.6557. Min Range: -5.6557

Max Act: 5.3119. Min Act: -0.1700

Data Index: 1337278 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 5.6557. Min Range: -5.6557

Max Act: 5.3119. Min Act: -0.1700

Data Index: 738159 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 5.6557. Min Range: -5.6557

Max Act: 5.2807. Min Act: -0.1700

Data Index: 726154 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 5.6557. Min Range: -5.6557

Max Act: 5.2807. Min Act: -0.1700

Data Index: 575710 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 5.6557. Min Range: -5.6557

Max Act: 5.2807. Min Act: -0.1700

Data Index: 1304181 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 5.6557. Min Range: -5.6557

Max Act: 5.2494. Min Act: -0.1700

Data Index: 830859 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 5.6557. Min Range: -5.6557

Max Act: 5.2182. Min Act: -0.1700

Data Index: 1587252 (Python Code)

Max Activating Token Index: 937

Text #10

Max Range: 5.6557. Min Range: -5.6557

Max Act: 5.0932. Min Act: -0.1700

Data Index: 311351 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 5.6557. Min Range: -5.6557

Max Act: 5.0619. Min Act: -0.1700

Data Index: 786792 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 5.6557. Min Range: -5.6557

Max Act: 5.0307. Min Act: -0.1700

Data Index: 448069 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 5.6557. Min Range: -5.6557

Max Act: 5.0619. Min Act: -0.1700

Data Index: 450239 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 5.6557. Min Range: -5.6557

Max Act: 5.0307. Min Act: -0.1700

Data Index: 895494 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 5.6557. Min Range: -5.6557

Max Act: 4.9682. Min Act: -0.1700

Data Index: 651023 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 5.6557. Min Range: -5.6557

Max Act: 4.9994. Min Act: -0.1700

Data Index: 1151518 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 5.6557. Min Range: -5.6557

Max Act: 4.9994. Min Act: -0.1700

Data Index: 4848 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 5.6557. Min Range: -5.6557

Max Act: 4.9682. Min Act: -0.1700

Data Index: 139164 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 5.6557. Min Range: -5.6557

Max Act: 4.9682. Min Act: -0.1700

Data Index: 1186737 (C4 (Web Text))

Max Activating Token Index: 227