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

Dataset: Open Web Text

Neuron 1984 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: 2.1101. Min Range: -2.1101

Max Act: 2.1101. Min Act: -0.1700

Data Index: 5002953 (Open Web Text)

Max Activating Token Index: 155

Text #1

Max Range: 2.1101. Min Range: -2.1101

Max Act: 2.0382. Min Act: -0.1700

Data Index: 6862536 (Open Web Text)

Max Activating Token Index: 969

Text #2

Max Range: 2.1101. Min Range: -2.1101

Max Act: 2.0347. Min Act: -0.1700

Data Index: 5054026 (Open Web Text)

Max Activating Token Index: 759

Text #3

Max Range: 2.1101. Min Range: -2.1101

Max Act: 2.0181. Min Act: -0.1698

Data Index: 4765372 (Open Web Text)

Max Activating Token Index: 580

Text #4

Max Range: 2.1101. Min Range: -2.1101

Max Act: 1.9919. Min Act: -0.1700

Data Index: 5714357 (Open Web Text)

Max Activating Token Index: 390

Text #5

Max Range: 2.1101. Min Range: -2.1101

Max Act: 1.9965. Min Act: -0.1700

Data Index: 5144269 (Open Web Text)

Max Activating Token Index: 161

Text #6

Max Range: 2.1101. Min Range: -2.1101

Max Act: 1.9843. Min Act: -0.1700

Data Index: 3122195 (Open Web Text)

Max Activating Token Index: 492

Text #7

Max Range: 2.1101. Min Range: -2.1101

Max Act: 1.9765. Min Act: -0.1700

Data Index: 4143181 (Open Web Text)

Max Activating Token Index: 424

Text #8

Max Range: 2.1101. Min Range: -2.1101

Max Act: 1.9453. Min Act: -0.1700

Data Index: 1068906 (Open Web Text)

Max Activating Token Index: 677

Text #9

Max Range: 2.1101. Min Range: -2.1101

Max Act: 1.9628. Min Act: -0.1700

Data Index: 5726251 (Open Web Text)

Max Activating Token Index: 765

Text #10

Max Range: 2.1101. Min Range: -2.1101

Max Act: 1.9660. Min Act: -0.1700

Data Index: 8729605 (Open Web Text)

Max Activating Token Index: 389

Text #11

Max Range: 2.1101. Min Range: -2.1101

Max Act: 1.9493. Min Act: -0.1700

Data Index: 1383769 (Open Web Text)

Max Activating Token Index: 423

Text #12

Max Range: 2.1101. Min Range: -2.1101

Max Act: 1.9703. Min Act: -0.1700

Data Index: 4673223 (Open Web Text)

Max Activating Token Index: 343

Text #13

Max Range: 2.1101. Min Range: -2.1101

Max Act: 1.9215. Min Act: -0.1700

Data Index: 8412643 (Open Web Text)

Max Activating Token Index: 195

Text #14

Max Range: 2.1101. Min Range: -2.1101

Max Act: 1.9367. Min Act: -0.1700

Data Index: 523546 (Open Web Text)

Max Activating Token Index: 632

Text #15

Max Range: 2.1101. Min Range: -2.1101

Max Act: 1.9377. Min Act: -0.1700

Data Index: 238473 (Open Web Text)

Max Activating Token Index: 259

Text #16

Max Range: 2.1101. Min Range: -2.1101

Max Act: 1.9398. Min Act: -0.1700

Data Index: 3783259 (Open Web Text)

Max Activating Token Index: 912

Text #17

Max Range: 2.1101. Min Range: -2.1101

Max Act: 1.9356. Min Act: -0.1700

Data Index: 3749713 (Open Web Text)

Max Activating Token Index: 118

Text #18

Max Range: 2.1101. Min Range: -2.1101

Max Act: 1.9166. Min Act: -0.1700

Data Index: 587584 (Open Web Text)

Max Activating Token Index: 611

Text #19

Max Range: 2.1101. Min Range: -2.1101

Max Act: 1.9063. Min Act: -0.1700

Data Index: 3749711 (Open Web Text)

Max Activating Token Index: 717