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

Dataset: Open Web Text

Neuron 2454 in Layer 4

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: 4.9432. Min Range: -4.9432

Max Act: 4.9432. Min Act: -0.1700

Data Index: 2374261 (Open Web Text)

Max Activating Token Index: 387

Text #1

Max Range: 4.9432. Min Range: -4.9432

Max Act: 4.7377. Min Act: -0.1700

Data Index: 6395513 (Open Web Text)

Max Activating Token Index: 538

Text #2

Max Range: 4.9432. Min Range: -4.9432

Max Act: 4.7270. Min Act: -0.1700

Data Index: 500887 (Open Web Text)

Max Activating Token Index: 614

Text #3

Max Range: 4.9432. Min Range: -4.9432

Max Act: 4.6884. Min Act: -0.1700

Data Index: 3282990 (Open Web Text)

Max Activating Token Index: 961

Text #4

Max Range: 4.9432. Min Range: -4.9432

Max Act: 4.7090. Min Act: -0.1700

Data Index: 4166039 (Open Web Text)

Max Activating Token Index: 362

Text #5

Max Range: 4.9432. Min Range: -4.9432

Max Act: 4.6889. Min Act: -0.1700

Data Index: 7649778 (Open Web Text)

Max Activating Token Index: 272

Text #6

Max Range: 4.9432. Min Range: -4.9432

Max Act: 4.5940. Min Act: -0.1700

Data Index: 6882117 (Open Web Text)

Max Activating Token Index: 618

Text #7

Max Range: 4.9432. Min Range: -4.9432

Max Act: 4.6023. Min Act: -0.1700

Data Index: 3693939 (Open Web Text)

Max Activating Token Index: 997

Text #8

Max Range: 4.9432. Min Range: -4.9432

Max Act: 4.5908. Min Act: -0.1700

Data Index: 310898 (Open Web Text)

Max Activating Token Index: 43

Text #9

Max Range: 4.9432. Min Range: -4.9432

Max Act: 4.6120. Min Act: -0.1700

Data Index: 3126633 (Open Web Text)

Max Activating Token Index: 520

Text #10

Max Range: 4.9432. Min Range: -4.9432

Max Act: 4.5970. Min Act: -0.1700

Data Index: 4380604 (Open Web Text)

Max Activating Token Index: 203

Text #11

Max Range: 4.9432. Min Range: -4.9432

Max Act: 4.5932. Min Act: -0.1700

Data Index: 7044874 (Open Web Text)

Max Activating Token Index: 187

Text #12

Max Range: 4.9432. Min Range: -4.9432

Max Act: 4.5652. Min Act: -0.1700

Data Index: 6303166 (Open Web Text)

Max Activating Token Index: 43

Text #13

Max Range: 4.9432. Min Range: -4.9432

Max Act: 4.5432. Min Act: -0.1700

Data Index: 2607908 (Open Web Text)

Max Activating Token Index: 949

Text #14

Max Range: 4.9432. Min Range: -4.9432

Max Act: 4.5290. Min Act: -0.1700

Data Index: 2613257 (Open Web Text)

Max Activating Token Index: 987

Text #15

Max Range: 4.9432. Min Range: -4.9432

Max Act: 4.5370. Min Act: -0.1700

Data Index: 5432241 (Open Web Text)

Max Activating Token Index: 917

Text #16

Max Range: 4.9432. Min Range: -4.9432

Max Act: 4.5555. Min Act: -0.1700

Data Index: 8099632 (Open Web Text)

Max Activating Token Index: 126

Text #17

Max Range: 4.9432. Min Range: -4.9432

Max Act: 4.5424. Min Act: -0.1700

Data Index: 8563638 (Open Web Text)

Max Activating Token Index: 705

Text #18

Max Range: 4.9432. Min Range: -4.9432

Max Act: 4.5197. Min Act: -0.1700

Data Index: 2737807 (Open Web Text)

Max Activating Token Index: 521

Text #19

Max Range: 4.9432. Min Range: -4.9432

Max Act: 4.5184. Min Act: -0.1700

Data Index: 1729709 (Open Web Text)

Max Activating Token Index: 914