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

Dataset: Open Web Text

Neuron 2829 in Layer 6

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: 4.5588. Min Range: -4.5588

Max Act: 4.5588. Min Act: -0.1700

Data Index: 3028821 (Open Web Text)

Max Activating Token Index: 469

Text #1

Max Range: 4.5588. Min Range: -4.5588

Max Act: 4.4571. Min Act: -0.1700

Data Index: 2472769 (Open Web Text)

Max Activating Token Index: 482

Text #2

Max Range: 4.5588. Min Range: -4.5588

Max Act: 4.3770. Min Act: -0.1700

Data Index: 2211897 (Open Web Text)

Max Activating Token Index: 195

Text #3

Max Range: 4.5588. Min Range: -4.5588

Max Act: 4.4059. Min Act: -0.1700

Data Index: 2676906 (Open Web Text)

Max Activating Token Index: 276

Text #4

Max Range: 4.5588. Min Range: -4.5588

Max Act: 4.3727. Min Act: -0.1700

Data Index: 2802380 (Open Web Text)

Max Activating Token Index: 880

Text #5

Max Range: 4.5588. Min Range: -4.5588

Max Act: 4.3489. Min Act: -0.1700

Data Index: 8270807 (Open Web Text)

Max Activating Token Index: 17

Text #6

Max Range: 4.5588. Min Range: -4.5588

Max Act: 4.3132. Min Act: -0.1700

Data Index: 2472768 (Open Web Text)

Max Activating Token Index: 1013

Text #7

Max Range: 4.5588. Min Range: -4.5588

Max Act: 4.2803. Min Act: -0.1700

Data Index: 4622895 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 4.5588. Min Range: -4.5588

Max Act: 4.2444. Min Act: -0.1700

Data Index: 5086707 (Open Web Text)

Max Activating Token Index: 808

Text #9

Max Range: 4.5588. Min Range: -4.5588

Max Act: 4.2635. Min Act: -0.1700

Data Index: 4651079 (Open Web Text)

Max Activating Token Index: 910

Text #10

Max Range: 4.5588. Min Range: -4.5588

Max Act: 4.2478. Min Act: -0.1700

Data Index: 8636866 (Open Web Text)

Max Activating Token Index: 319

Text #11

Max Range: 4.5588. Min Range: -4.5588

Max Act: 4.2032. Min Act: -0.1700

Data Index: 5059905 (Open Web Text)

Max Activating Token Index: 558

Text #12

Max Range: 4.5588. Min Range: -4.5588

Max Act: 4.2234. Min Act: -0.1700

Data Index: 8170891 (Open Web Text)

Max Activating Token Index: 313

Text #13

Max Range: 4.5588. Min Range: -4.5588

Max Act: 4.2274. Min Act: -0.1700

Data Index: 603539 (Open Web Text)

Max Activating Token Index: 478

Text #14

Max Range: 4.5588. Min Range: -4.5588

Max Act: 4.1895. Min Act: -0.1700

Data Index: 1142803 (Open Web Text)

Max Activating Token Index: 496

Text #15

Max Range: 4.5588. Min Range: -4.5588

Max Act: 4.1778. Min Act: -0.1700

Data Index: 7385872 (Open Web Text)

Max Activating Token Index: 981

Text #16

Max Range: 4.5588. Min Range: -4.5588

Max Act: 4.1771. Min Act: -0.1700

Data Index: 7120590 (Open Web Text)

Max Activating Token Index: 115

Text #17

Max Range: 4.5588. Min Range: -4.5588

Max Act: 4.1629. Min Act: -0.1700

Data Index: 7100389 (Open Web Text)

Max Activating Token Index: 505

Text #18

Max Range: 4.5588. Min Range: -4.5588

Max Act: 4.1626. Min Act: -0.1700

Data Index: 2025603 (Open Web Text)

Max Activating Token Index: 984

Text #19

Max Range: 4.5588. Min Range: -4.5588

Max Act: 4.1306. Min Act: -0.1700

Data Index: 1760461 (Open Web Text)

Max Activating Token Index: 81