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

Dataset: Open Web Text

Neuron 2553 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: 4.0334. Min Range: -4.0334

Max Act: 4.0334. Min Act: -0.1700

Data Index: 5535069 (Open Web Text)

Max Activating Token Index: 734

Text #1

Max Range: 4.0334. Min Range: -4.0334

Max Act: 3.9767. Min Act: -0.1700

Data Index: 3897789 (Open Web Text)

Max Activating Token Index: 395

Text #2

Max Range: 4.0334. Min Range: -4.0334

Max Act: 3.8249. Min Act: -0.1700

Data Index: 8628569 (Open Web Text)

Max Activating Token Index: 849

Text #3

Max Range: 4.0334. Min Range: -4.0334

Max Act: 3.7953. Min Act: -0.1700

Data Index: 4221774 (Open Web Text)

Max Activating Token Index: 86

Text #4

Max Range: 4.0334. Min Range: -4.0334

Max Act: 3.7645. Min Act: -0.1700

Data Index: 7757836 (Open Web Text)

Max Activating Token Index: 362

Text #5

Max Range: 4.0334. Min Range: -4.0334

Max Act: 3.7764. Min Act: -0.1700

Data Index: 1562757 (Open Web Text)

Max Activating Token Index: 67

Text #6

Max Range: 4.0334. Min Range: -4.0334

Max Act: 3.7743. Min Act: -0.1700

Data Index: 7751888 (Open Web Text)

Max Activating Token Index: 766

Text #7

Max Range: 4.0334. Min Range: -4.0334

Max Act: 3.7253. Min Act: -0.1700

Data Index: 163806 (Open Web Text)

Max Activating Token Index: 725

Text #8

Max Range: 4.0334. Min Range: -4.0334

Max Act: 3.7630. Min Act: -0.1700

Data Index: 7166237 (Open Web Text)

Max Activating Token Index: 741

Text #9

Max Range: 4.0334. Min Range: -4.0334

Max Act: 3.7111. Min Act: -0.1700

Data Index: 5943870 (Open Web Text)

Max Activating Token Index: 29

Text #10

Max Range: 4.0334. Min Range: -4.0334

Max Act: 3.7232. Min Act: -0.1700

Data Index: 4649173 (Open Web Text)

Max Activating Token Index: 398

Text #11

Max Range: 4.0334. Min Range: -4.0334

Max Act: 3.7347. Min Act: -0.1700

Data Index: 3025690 (Open Web Text)

Max Activating Token Index: 334

Text #12

Max Range: 4.0334. Min Range: -4.0334

Max Act: 3.6947. Min Act: -0.1700

Data Index: 5860697 (Open Web Text)

Max Activating Token Index: 946

Text #13

Max Range: 4.0334. Min Range: -4.0334

Max Act: 3.7334. Min Act: -0.1700

Data Index: 4888200 (Open Web Text)

Max Activating Token Index: 78

Text #14

Max Range: 4.0334. Min Range: -4.0334

Max Act: 3.6992. Min Act: -0.1700

Data Index: 3330690 (Open Web Text)

Max Activating Token Index: 598

Text #15

Max Range: 4.0334. Min Range: -4.0334

Max Act: 3.6192. Min Act: -0.1700

Data Index: 1107667 (Open Web Text)

Max Activating Token Index: 507

Text #16

Max Range: 4.0334. Min Range: -4.0334

Max Act: 3.7335. Min Act: -0.1700

Data Index: 1010180 (Open Web Text)

Max Activating Token Index: 343

Text #17

Max Range: 4.0334. Min Range: -4.0334

Max Act: 3.6811. Min Act: -0.1700

Data Index: 5081722 (Open Web Text)

Max Activating Token Index: 620

Text #18

Max Range: 4.0334. Min Range: -4.0334

Max Act: 3.7083. Min Act: -0.1700

Data Index: 1559709 (Open Web Text)

Max Activating Token Index: 757

Text #19

Max Range: 4.0334. Min Range: -4.0334

Max Act: 3.7157. Min Act: -0.1700

Data Index: 4026616 (Open Web Text)

Max Activating Token Index: 264