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

Dataset: Open Web Text

Neuron 1226 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: 4.0732. Min Range: -4.0732

Max Act: 4.0732. Min Act: -0.1700

Data Index: 4346682 (Open Web Text)

Max Activating Token Index: 910

Text #1

Max Range: 4.0732. Min Range: -4.0732

Max Act: 3.9693. Min Act: -0.1700

Data Index: 3275681 (Open Web Text)

Max Activating Token Index: 525

Text #2

Max Range: 4.0732. Min Range: -4.0732

Max Act: 3.9151. Min Act: -0.1700

Data Index: 7298442 (Open Web Text)

Max Activating Token Index: 284

Text #3

Max Range: 4.0732. Min Range: -4.0732

Max Act: 3.8679. Min Act: -0.1700

Data Index: 467236 (Open Web Text)

Max Activating Token Index: 393

Text #4

Max Range: 4.0732. Min Range: -4.0732

Max Act: 3.8423. Min Act: -0.1700

Data Index: 2342431 (Open Web Text)

Max Activating Token Index: 561

Text #5

Max Range: 4.0732. Min Range: -4.0732

Max Act: 3.8159. Min Act: -0.1700

Data Index: 2563113 (Open Web Text)

Max Activating Token Index: 198

Text #6

Max Range: 4.0732. Min Range: -4.0732

Max Act: 3.8448. Min Act: -0.1700

Data Index: 4358011 (Open Web Text)

Max Activating Token Index: 628

Text #7

Max Range: 4.0732. Min Range: -4.0732

Max Act: 3.8004. Min Act: -0.1700

Data Index: 1269477 (Open Web Text)

Max Activating Token Index: 958

Text #8

Max Range: 4.0732. Min Range: -4.0732

Max Act: 3.8148. Min Act: -0.1700

Data Index: 1963271 (Open Web Text)

Max Activating Token Index: 415

Text #9

Max Range: 4.0732. Min Range: -4.0732

Max Act: 3.7714. Min Act: -0.1700

Data Index: 1921327 (Open Web Text)

Max Activating Token Index: 912

Text #10

Max Range: 4.0732. Min Range: -4.0732

Max Act: 3.7854. Min Act: -0.1700

Data Index: 4458586 (Open Web Text)

Max Activating Token Index: 541

Text #11

Max Range: 4.0732. Min Range: -4.0732

Max Act: 3.7797. Min Act: -0.1700

Data Index: 8671447 (Open Web Text)

Max Activating Token Index: 767

Text #12

Max Range: 4.0732. Min Range: -4.0732

Max Act: 3.8026. Min Act: -0.1700

Data Index: 4618850 (Open Web Text)

Max Activating Token Index: 67

Text #13

Max Range: 4.0732. Min Range: -4.0732

Max Act: 3.7667. Min Act: -0.1700

Data Index: 2605158 (Open Web Text)

Max Activating Token Index: 917

Text #14

Max Range: 4.0732. Min Range: -4.0732

Max Act: 3.7481. Min Act: -0.1700

Data Index: 7365148 (Open Web Text)

Max Activating Token Index: 417

Text #15

Max Range: 4.0732. Min Range: -4.0732

Max Act: 3.7946. Min Act: -0.1700

Data Index: 1276326 (Open Web Text)

Max Activating Token Index: 261

Text #16

Max Range: 4.0732. Min Range: -4.0732

Max Act: 3.7732. Min Act: -0.1700

Data Index: 5882490 (Open Web Text)

Max Activating Token Index: 295

Text #17

Max Range: 4.0732. Min Range: -4.0732

Max Act: 3.7805. Min Act: -0.1700

Data Index: 5609981 (Open Web Text)

Max Activating Token Index: 364

Text #18

Max Range: 4.0732. Min Range: -4.0732

Max Act: 3.7460. Min Act: -0.1700

Data Index: 6086694 (Open Web Text)

Max Activating Token Index: 692

Text #19

Max Range: 4.0732. Min Range: -4.0732

Max Act: 3.7265. Min Act: -0.1700

Data Index: 4585457 (Open Web Text)

Max Activating Token Index: 235