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

Dataset: Open Web Text

Neuron 1340 in Layer 2

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: 1.8466. Min Range: -1.8466

Max Act: 1.8466. Min Act: -0.1700

Data Index: 2507265 (Open Web Text)

Max Activating Token Index: 188

Text #1

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.7071. Min Act: -0.1700

Data Index: 7932359 (Open Web Text)

Max Activating Token Index: 569

Text #2

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6783. Min Act: -0.1700

Data Index: 432535 (Open Web Text)

Max Activating Token Index: 166

Text #3

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6870. Min Act: -0.1700

Data Index: 2438930 (Open Web Text)

Max Activating Token Index: 926

Text #4

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6784. Min Act: -0.1700

Data Index: 3260495 (Open Web Text)

Max Activating Token Index: 101

Text #5

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6753. Min Act: -0.1700

Data Index: 357308 (Open Web Text)

Max Activating Token Index: 508

Text #6

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6702. Min Act: -0.1700

Data Index: 5954131 (Open Web Text)

Max Activating Token Index: 219

Text #7

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6795. Min Act: -0.1700

Data Index: 3056472 (Open Web Text)

Max Activating Token Index: 539

Text #8

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6678. Min Act: -0.1700

Data Index: 2507264 (Open Web Text)

Max Activating Token Index: 460

Text #9

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6714. Min Act: -0.1700

Data Index: 2603171 (Open Web Text)

Max Activating Token Index: 587

Text #10

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6692. Min Act: -0.1700

Data Index: 4222010 (Open Web Text)

Max Activating Token Index: 656

Text #11

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6520. Min Act: -0.1700

Data Index: 5913161 (Open Web Text)

Max Activating Token Index: 424

Text #12

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6514. Min Act: -0.1700

Data Index: 6721226 (Open Web Text)

Max Activating Token Index: 412

Text #13

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6443. Min Act: -0.1700

Data Index: 5575540 (Open Web Text)

Max Activating Token Index: 325

Text #14

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6556. Min Act: -0.1700

Data Index: 7317024 (Open Web Text)

Max Activating Token Index: 161

Text #15

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6439. Min Act: -0.1698

Data Index: 6108911 (Open Web Text)

Max Activating Token Index: 718

Text #16

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6549. Min Act: -0.1698

Data Index: 2830991 (Open Web Text)

Max Activating Token Index: 1021

Text #17

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6445. Min Act: -0.1700

Data Index: 4359784 (Open Web Text)

Max Activating Token Index: 1009

Text #18

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6377. Min Act: -0.1700

Data Index: 6301040 (Open Web Text)

Max Activating Token Index: 700

Text #19

Max Range: 1.8466. Min Range: -1.8466

Max Act: 1.6451. Min Act: -0.1700

Data Index: 5399986 (Open Web Text)

Max Activating Token Index: 165