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

Dataset: Open Web Text

Neuron 451 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: 3.0348. Min Range: -3.0348

Max Act: 3.0348. Min Act: -0.1700

Data Index: 1483614 (Open Web Text)

Max Activating Token Index: 899

Text #1

Max Range: 3.0348. Min Range: -3.0348

Max Act: 2.9350. Min Act: -0.1700

Data Index: 2432247 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 3.0348. Min Range: -3.0348

Max Act: 2.8518. Min Act: -0.1700

Data Index: 5645728 (Open Web Text)

Max Activating Token Index: 530

Text #3

Max Range: 3.0348. Min Range: -3.0348

Max Act: 2.8430. Min Act: -0.1700

Data Index: 5645741 (Open Web Text)

Max Activating Token Index: 483

Text #4

Max Range: 3.0348. Min Range: -3.0348

Max Act: 2.8643. Min Act: -0.1700

Data Index: 8131029 (Open Web Text)

Max Activating Token Index: 849

Text #5

Max Range: 3.0348. Min Range: -3.0348

Max Act: 2.8293. Min Act: -0.1700

Data Index: 3954411 (Open Web Text)

Max Activating Token Index: 752

Text #6

Max Range: 3.0348. Min Range: -3.0348

Max Act: 2.8193. Min Act: -0.1700

Data Index: 263685 (Open Web Text)

Max Activating Token Index: 665

Text #7

Max Range: 3.0348. Min Range: -3.0348

Max Act: 2.8176. Min Act: -0.1700

Data Index: 5065279 (Open Web Text)

Max Activating Token Index: 807

Text #8

Max Range: 3.0348. Min Range: -3.0348

Max Act: 2.8080. Min Act: -0.1700

Data Index: 263684 (Open Web Text)

Max Activating Token Index: 518

Text #9

Max Range: 3.0348. Min Range: -3.0348

Max Act: 2.7832. Min Act: -0.1700

Data Index: 4617083 (Open Web Text)

Max Activating Token Index: 803

Text #10

Max Range: 3.0348. Min Range: -3.0348

Max Act: 2.8069. Min Act: -0.1700

Data Index: 1281737 (Open Web Text)

Max Activating Token Index: 279

Text #11

Max Range: 3.0348. Min Range: -3.0348

Max Act: 2.7872. Min Act: -0.1700

Data Index: 400982 (Open Web Text)

Max Activating Token Index: 577

Text #12

Max Range: 3.0348. Min Range: -3.0348

Max Act: 2.7877. Min Act: -0.1700

Data Index: 8469871 (Open Web Text)

Max Activating Token Index: 122

Text #13

Max Range: 3.0348. Min Range: -3.0348

Max Act: 2.7708. Min Act: -0.1700

Data Index: 5085958 (Open Web Text)

Max Activating Token Index: 877

Text #14

Max Range: 3.0348. Min Range: -3.0348

Max Act: 2.7772. Min Act: -0.1700

Data Index: 6531176 (Open Web Text)

Max Activating Token Index: 941

Text #15

Max Range: 3.0348. Min Range: -3.0348

Max Act: 2.7396. Min Act: -0.1700

Data Index: 8131023 (Open Web Text)

Max Activating Token Index: 192

Text #16

Max Range: 3.0348. Min Range: -3.0348

Max Act: 2.7482. Min Act: -0.1700

Data Index: 7646737 (Open Web Text)

Max Activating Token Index: 428

Text #17

Max Range: 3.0348. Min Range: -3.0348

Max Act: 2.7724. Min Act: -0.1700

Data Index: 2204029 (Open Web Text)

Max Activating Token Index: 632

Text #18

Max Range: 3.0348. Min Range: -3.0348

Max Act: 2.7529. Min Act: -0.1700

Data Index: 3950805 (Open Web Text)

Max Activating Token Index: 117

Text #19

Max Range: 3.0348. Min Range: -3.0348

Max Act: 2.7504. Min Act: -0.1700

Data Index: 3355838 (Open Web Text)

Max Activating Token Index: 663