Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2103 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4587. Min Act: -0.1700

Data Index: 1128729 (Open Web Text)

Max Activating Token Index: 986

Text #1

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4586. Min Act: -0.1700

Data Index: 296171 (Open Web Text)

Max Activating Token Index: 999

Text #2

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4352. Min Act: -0.1700

Data Index: 8640470 (Open Web Text)

Max Activating Token Index: 1013

Text #3

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4246. Min Act: -0.1700

Data Index: 8768325 (Open Web Text)

Max Activating Token Index: 1019

Text #4

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4076. Min Act: -0.1700

Data Index: 4976583 (Open Web Text)

Max Activating Token Index: 832

Text #5

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3974. Min Act: -0.1700

Data Index: 1033614 (Open Web Text)

Max Activating Token Index: 864

Text #6

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4073. Min Act: -0.1700

Data Index: 3624620 (Open Web Text)

Max Activating Token Index: 965

Text #7

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3868. Min Act: -0.1700

Data Index: 7099583 (Open Web Text)

Max Activating Token Index: 855

Text #8

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3827. Min Act: -0.1700

Data Index: 7799307 (Open Web Text)

Max Activating Token Index: 716

Text #9

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3741. Min Act: -0.1700

Data Index: 2676753 (Open Web Text)

Max Activating Token Index: 834

Text #10

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3743. Min Act: -0.1700

Data Index: 4262176 (Open Web Text)

Max Activating Token Index: 938

Text #11

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3674. Min Act: -0.1700

Data Index: 682777 (Open Web Text)

Max Activating Token Index: 911

Text #12

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3685. Min Act: -0.1700

Data Index: 6274027 (Open Web Text)

Max Activating Token Index: 858

Text #13

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3596. Min Act: -0.1700

Data Index: 2528370 (Open Web Text)

Max Activating Token Index: 782

Text #14

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3458. Min Act: -0.1700

Data Index: 3579806 (Open Web Text)

Max Activating Token Index: 1017

Text #15

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3568. Min Act: -0.1700

Data Index: 3878142 (Open Web Text)

Max Activating Token Index: 997

Text #16

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3516. Min Act: -0.1700

Data Index: 1128143 (Open Web Text)

Max Activating Token Index: 729

Text #17

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3514. Min Act: -0.1700

Data Index: 5770889 (Open Web Text)

Max Activating Token Index: 988

Text #18

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3304. Min Act: -0.1700

Data Index: 6132428 (Open Web Text)

Max Activating Token Index: 866

Text #19

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3400. Min Act: -0.1700

Data Index: 6359317 (Open Web Text)

Max Activating Token Index: 1004