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

Dataset: Open Web Text

Neuron 3054 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: 7.5731. Min Range: -7.5731

Max Act: 7.5731. Min Act: -0.1700

Data Index: 7838016 (Open Web Text)

Max Activating Token Index: 549

Text #1

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.3212. Min Act: -0.1700

Data Index: 6512347 (Open Web Text)

Max Activating Token Index: 768

Text #2

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.3335. Min Act: -0.1700

Data Index: 6399089 (Open Web Text)

Max Activating Token Index: 817

Text #3

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.3284. Min Act: -0.1700

Data Index: 4472686 (Open Web Text)

Max Activating Token Index: 194

Text #4

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.3207. Min Act: -0.1700

Data Index: 3731247 (Open Web Text)

Max Activating Token Index: 584

Text #5

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.2590. Min Act: -0.1700

Data Index: 6633366 (Open Web Text)

Max Activating Token Index: 619

Text #6

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.2164. Min Act: -0.1700

Data Index: 2692082 (Open Web Text)

Max Activating Token Index: 972

Text #7

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.2088. Min Act: -0.1700

Data Index: 6780457 (Open Web Text)

Max Activating Token Index: 358

Text #8

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.2193. Min Act: -0.1700

Data Index: 4322493 (Open Web Text)

Max Activating Token Index: 97

Text #9

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.1484. Min Act: -0.1700

Data Index: 4722051 (Open Web Text)

Max Activating Token Index: 286

Text #10

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.1683. Min Act: -0.1700

Data Index: 5803391 (Open Web Text)

Max Activating Token Index: 124

Text #11

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.0572. Min Act: -0.1700

Data Index: 5758735 (Open Web Text)

Max Activating Token Index: 844

Text #12

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.0243. Min Act: -0.1700

Data Index: 3920408 (Open Web Text)

Max Activating Token Index: 74

Text #13

Max Range: 7.5731. Min Range: -7.5731

Max Act: 6.9205. Min Act: -0.1700

Data Index: 5320610 (Open Web Text)

Max Activating Token Index: 956

Text #14

Max Range: 7.5731. Min Range: -7.5731

Max Act: 6.8954. Min Act: -0.1700

Data Index: 5934292 (Open Web Text)

Max Activating Token Index: 722

Text #15

Max Range: 7.5731. Min Range: -7.5731

Max Act: 6.8131. Min Act: -0.1700

Data Index: 510412 (Open Web Text)

Max Activating Token Index: 464

Text #16

Max Range: 7.5731. Min Range: -7.5731

Max Act: 6.8755. Min Act: -0.1700

Data Index: 5532027 (Open Web Text)

Max Activating Token Index: 237

Text #17

Max Range: 7.5731. Min Range: -7.5731

Max Act: 6.8612. Min Act: -0.1700

Data Index: 8594578 (Open Web Text)

Max Activating Token Index: 765

Text #18

Max Range: 7.5731. Min Range: -7.5731

Max Act: 6.7786. Min Act: -0.1700

Data Index: 580876 (Open Web Text)

Max Activating Token Index: 929

Text #19

Max Range: 7.5731. Min Range: -7.5731

Max Act: 6.8206. Min Act: -0.1700

Data Index: 3270713 (Open Web Text)

Max Activating Token Index: 861