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

Dataset: Open Web Text

Neuron 106 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: 3.0761. Min Range: -3.0761

Max Act: 3.0761. Min Act: -0.1700

Data Index: 556467 (Open Web Text)

Max Activating Token Index: 446

Text #1

Max Range: 3.0761. Min Range: -3.0761

Max Act: 3.0009. Min Act: -0.1700

Data Index: 4476112 (Open Web Text)

Max Activating Token Index: 432

Text #2

Max Range: 3.0761. Min Range: -3.0761

Max Act: 2.9958. Min Act: -0.1700

Data Index: 5540017 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 3.0761. Min Range: -3.0761

Max Act: 2.9891. Min Act: -0.1700

Data Index: 8551306 (Open Web Text)

Max Activating Token Index: 308

Text #4

Max Range: 3.0761. Min Range: -3.0761

Max Act: 2.9681. Min Act: -0.1700

Data Index: 888329 (Open Web Text)

Max Activating Token Index: 392

Text #5

Max Range: 3.0761. Min Range: -3.0761

Max Act: 2.9725. Min Act: -0.1700

Data Index: 542971 (Open Web Text)

Max Activating Token Index: 19

Text #6

Max Range: 3.0761. Min Range: -3.0761

Max Act: 2.9741. Min Act: -0.1700

Data Index: 3998911 (Open Web Text)

Max Activating Token Index: 144

Text #7

Max Range: 3.0761. Min Range: -3.0761

Max Act: 2.9891. Min Act: -0.1700

Data Index: 7700596 (Open Web Text)

Max Activating Token Index: 465

Text #8

Max Range: 3.0761. Min Range: -3.0761

Max Act: 2.9717. Min Act: -0.1700

Data Index: 7180792 (Open Web Text)

Max Activating Token Index: 569

Text #9

Max Range: 3.0761. Min Range: -3.0761

Max Act: 2.9786. Min Act: -0.1700

Data Index: 3652944 (Open Web Text)

Max Activating Token Index: 928

Text #10

Max Range: 3.0761. Min Range: -3.0761

Max Act: 2.9614. Min Act: -0.1700

Data Index: 400081 (Open Web Text)

Max Activating Token Index: 363

Text #11

Max Range: 3.0761. Min Range: -3.0761

Max Act: 2.9453. Min Act: -0.1700

Data Index: 3545327 (Open Web Text)

Max Activating Token Index: 965

Text #12

Max Range: 3.0761. Min Range: -3.0761

Max Act: 2.9491. Min Act: -0.1700

Data Index: 741380 (Open Web Text)

Max Activating Token Index: 738

Text #13

Max Range: 3.0761. Min Range: -3.0761

Max Act: 2.9664. Min Act: -0.1700

Data Index: 5058793 (Open Web Text)

Max Activating Token Index: 191

Text #14

Max Range: 3.0761. Min Range: -3.0761

Max Act: 2.9418. Min Act: -0.1700

Data Index: 8180517 (Open Web Text)

Max Activating Token Index: 710

Text #15

Max Range: 3.0761. Min Range: -3.0761

Max Act: 2.9363. Min Act: -0.1700

Data Index: 2513087 (Open Web Text)

Max Activating Token Index: 485

Text #16

Max Range: 3.0761. Min Range: -3.0761

Max Act: 2.9383. Min Act: -0.1700

Data Index: 8419817 (Open Web Text)

Max Activating Token Index: 460

Text #17

Max Range: 3.0761. Min Range: -3.0761

Max Act: 2.9396. Min Act: -0.1700

Data Index: 5704387 (Open Web Text)

Max Activating Token Index: 769

Text #18

Max Range: 3.0761. Min Range: -3.0761

Max Act: 2.9341. Min Act: -0.1700

Data Index: 279018 (Open Web Text)

Max Activating Token Index: 289

Text #19

Max Range: 3.0761. Min Range: -3.0761

Max Act: 2.9208. Min Act: -0.1700

Data Index: 1079856 (Open Web Text)

Max Activating Token Index: 908