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

Dataset: Open Web Text

Neuron 2949 in Layer 2

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: 3.5450. Min Range: -3.5450

Max Act: 3.5337. Min Act: -0.1700

Data Index: 5257769 (Open Web Text)

Max Activating Token Index: 282

Text #1

Max Range: 3.5450. Min Range: -3.5450

Max Act: 3.5450. Min Act: -0.1700

Data Index: 4735905 (Open Web Text)

Max Activating Token Index: 389

Text #2

Max Range: 3.5450. Min Range: -3.5450

Max Act: 3.4759. Min Act: -0.1700

Data Index: 2160659 (Open Web Text)

Max Activating Token Index: 59

Text #3

Max Range: 3.5450. Min Range: -3.5450

Max Act: 3.4297. Min Act: -0.1700

Data Index: 5717272 (Open Web Text)

Max Activating Token Index: 72

Text #4

Max Range: 3.5450. Min Range: -3.5450

Max Act: 3.4473. Min Act: -0.1700

Data Index: 6258373 (Open Web Text)

Max Activating Token Index: 389

Text #5

Max Range: 3.5450. Min Range: -3.5450

Max Act: 3.4303. Min Act: -0.1700

Data Index: 4301061 (Open Web Text)

Max Activating Token Index: 381

Text #6

Max Range: 3.5450. Min Range: -3.5450

Max Act: 3.4568. Min Act: -0.1700

Data Index: 798315 (Open Web Text)

Max Activating Token Index: 573

Text #7

Max Range: 3.5450. Min Range: -3.5450

Max Act: 3.4245. Min Act: -0.1700

Data Index: 8022460 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 3.5450. Min Range: -3.5450

Max Act: 3.4295. Min Act: -0.1700

Data Index: 4376120 (Open Web Text)

Max Activating Token Index: 99

Text #9

Max Range: 3.5450. Min Range: -3.5450

Max Act: 3.4052. Min Act: -0.1700

Data Index: 8802253 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 3.5450. Min Range: -3.5450

Max Act: 3.4117. Min Act: -0.1700

Data Index: 1518622 (Open Web Text)

Max Activating Token Index: 728

Text #11

Max Range: 3.5450. Min Range: -3.5450

Max Act: 3.3734. Min Act: -0.1700

Data Index: 1513587 (Open Web Text)

Max Activating Token Index: 774

Text #12

Max Range: 3.5450. Min Range: -3.5450

Max Act: 3.4008. Min Act: -0.1700

Data Index: 5510234 (Open Web Text)

Max Activating Token Index: 912

Text #13

Max Range: 3.5450. Min Range: -3.5450

Max Act: 3.3743. Min Act: -0.1700

Data Index: 2467296 (Open Web Text)

Max Activating Token Index: 413

Text #14

Max Range: 3.5450. Min Range: -3.5450

Max Act: 3.4021. Min Act: -0.1700

Data Index: 7379866 (Open Web Text)

Max Activating Token Index: 953

Text #15

Max Range: 3.5450. Min Range: -3.5450

Max Act: 3.3861. Min Act: -0.1700

Data Index: 6912710 (Open Web Text)

Max Activating Token Index: 124

Text #16

Max Range: 3.5450. Min Range: -3.5450

Max Act: 3.3903. Min Act: -0.1700

Data Index: 2841942 (Open Web Text)

Max Activating Token Index: 83

Text #17

Max Range: 3.5450. Min Range: -3.5450

Max Act: 3.3598. Min Act: -0.1700

Data Index: 5017110 (Open Web Text)

Max Activating Token Index: 612

Text #18

Max Range: 3.5450. Min Range: -3.5450

Max Act: 3.3916. Min Act: -0.1700

Data Index: 5205635 (Open Web Text)

Max Activating Token Index: 300

Text #19

Max Range: 3.5450. Min Range: -3.5450

Max Act: 3.3768. Min Act: -0.1700

Data Index: 5307141 (Open Web Text)

Max Activating Token Index: 93