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

Dataset: Open Web Text

Neuron 2023 in Layer 3

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: 4.6895. Min Range: -4.6895

Max Act: 4.6895. Min Act: -0.1700

Data Index: 7416019 (Open Web Text)

Max Activating Token Index: 340

Text #1

Max Range: 4.6895. Min Range: -4.6895

Max Act: 4.6826. Min Act: -0.1700

Data Index: 5210953 (Open Web Text)

Max Activating Token Index: 894

Text #2

Max Range: 4.6895. Min Range: -4.6895

Max Act: 4.5998. Min Act: -0.1700

Data Index: 5975615 (Open Web Text)

Max Activating Token Index: 857

Text #3

Max Range: 4.6895. Min Range: -4.6895

Max Act: 4.6062. Min Act: -0.1700

Data Index: 786395 (Open Web Text)

Max Activating Token Index: 677

Text #4

Max Range: 4.6895. Min Range: -4.6895

Max Act: 4.6108. Min Act: -0.1700

Data Index: 6852158 (Open Web Text)

Max Activating Token Index: 869

Text #5

Max Range: 4.6895. Min Range: -4.6895

Max Act: 4.6030. Min Act: -0.1700

Data Index: 1338332 (Open Web Text)

Max Activating Token Index: 617

Text #6

Max Range: 4.6895. Min Range: -4.6895

Max Act: 4.5920. Min Act: -0.1700

Data Index: 3078469 (Open Web Text)

Max Activating Token Index: 234

Text #7

Max Range: 4.6895. Min Range: -4.6895

Max Act: 4.4831. Min Act: -0.1700

Data Index: 534941 (Open Web Text)

Max Activating Token Index: 484

Text #8

Max Range: 4.6895. Min Range: -4.6895

Max Act: 4.5494. Min Act: -0.1700

Data Index: 2084860 (Open Web Text)

Max Activating Token Index: 820

Text #9

Max Range: 4.6895. Min Range: -4.6895

Max Act: 4.5200. Min Act: -0.1700

Data Index: 4352031 (Open Web Text)

Max Activating Token Index: 271

Text #10

Max Range: 4.6895. Min Range: -4.6895

Max Act: 4.5422. Min Act: -0.1700

Data Index: 34344 (Open Web Text)

Max Activating Token Index: 108

Text #11

Max Range: 4.6895. Min Range: -4.6895

Max Act: 4.5457. Min Act: -0.1700

Data Index: 8741201 (Open Web Text)

Max Activating Token Index: 843

Text #12

Max Range: 4.6895. Min Range: -4.6895

Max Act: 4.4878. Min Act: -0.1700

Data Index: 3219466 (Open Web Text)

Max Activating Token Index: 35

Text #13

Max Range: 4.6895. Min Range: -4.6895

Max Act: 4.4936. Min Act: -0.1700

Data Index: 5347810 (Open Web Text)

Max Activating Token Index: 80

Text #14

Max Range: 4.6895. Min Range: -4.6895

Max Act: 4.5071. Min Act: -0.1700

Data Index: 6624183 (Open Web Text)

Max Activating Token Index: 439

Text #15

Max Range: 4.6895. Min Range: -4.6895

Max Act: 4.5886. Min Act: -0.1700

Data Index: 7433120 (Open Web Text)

Max Activating Token Index: 776

Text #16

Max Range: 4.6895. Min Range: -4.6895

Max Act: 4.4571. Min Act: -0.1700

Data Index: 2305300 (Open Web Text)

Max Activating Token Index: 88

Text #17

Max Range: 4.6895. Min Range: -4.6895

Max Act: 4.5692. Min Act: -0.1700

Data Index: 3894969 (Open Web Text)

Max Activating Token Index: 385

Text #18

Max Range: 4.6895. Min Range: -4.6895

Max Act: 4.4777. Min Act: -0.1700

Data Index: 5222034 (Open Web Text)

Max Activating Token Index: 631

Text #19

Max Range: 4.6895. Min Range: -4.6895

Max Act: 4.5017. Min Act: -0.1699

Data Index: 2891084 (Open Web Text)

Max Activating Token Index: 403