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

Dataset: Open Web Text

Neuron 714 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: 4.2699. Min Range: -4.2699

Max Act: 4.2699. Min Act: -0.1700

Data Index: 6564036 (Open Web Text)

Max Activating Token Index: 780

Text #1

Max Range: 4.2699. Min Range: -4.2699

Max Act: 4.1781. Min Act: -0.1700

Data Index: 7494533 (Open Web Text)

Max Activating Token Index: 558

Text #2

Max Range: 4.2699. Min Range: -4.2699

Max Act: 4.1323. Min Act: -0.1700

Data Index: 3869892 (Open Web Text)

Max Activating Token Index: 903

Text #3

Max Range: 4.2699. Min Range: -4.2699

Max Act: 4.1485. Min Act: -0.1700

Data Index: 603222 (Open Web Text)

Max Activating Token Index: 485

Text #4

Max Range: 4.2699. Min Range: -4.2699

Max Act: 4.1051. Min Act: -0.1700

Data Index: 1945289 (Open Web Text)

Max Activating Token Index: 495

Text #5

Max Range: 4.2699. Min Range: -4.2699

Max Act: 4.0936. Min Act: -0.1700

Data Index: 5628232 (Open Web Text)

Max Activating Token Index: 306

Text #6

Max Range: 4.2699. Min Range: -4.2699

Max Act: 4.1307. Min Act: -0.1700

Data Index: 1280118 (Open Web Text)

Max Activating Token Index: 273

Text #7

Max Range: 4.2699. Min Range: -4.2699

Max Act: 4.1157. Min Act: -0.1700

Data Index: 589877 (Open Web Text)

Max Activating Token Index: 554

Text #8

Max Range: 4.2699. Min Range: -4.2699

Max Act: 4.0467. Min Act: -0.1700

Data Index: 1349387 (Open Web Text)

Max Activating Token Index: 811

Text #9

Max Range: 4.2699. Min Range: -4.2699

Max Act: 4.0479. Min Act: -0.1700

Data Index: 2746540 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 4.2699. Min Range: -4.2699

Max Act: 4.0851. Min Act: -0.1700

Data Index: 2180154 (Open Web Text)

Max Activating Token Index: 22

Text #11

Max Range: 4.2699. Min Range: -4.2699

Max Act: 4.0340. Min Act: -0.1700

Data Index: 6858382 (Open Web Text)

Max Activating Token Index: 194

Text #12

Max Range: 4.2699. Min Range: -4.2699

Max Act: 4.0530. Min Act: -0.1700

Data Index: 4714123 (Open Web Text)

Max Activating Token Index: 974

Text #13

Max Range: 4.2699. Min Range: -4.2699

Max Act: 4.0210. Min Act: -0.1700

Data Index: 5020658 (Open Web Text)

Max Activating Token Index: 620

Text #14

Max Range: 4.2699. Min Range: -4.2699

Max Act: 4.0188. Min Act: -0.1700

Data Index: 7220878 (Open Web Text)

Max Activating Token Index: 507

Text #15

Max Range: 4.2699. Min Range: -4.2699

Max Act: 4.0021. Min Act: -0.1700

Data Index: 5099702 (Open Web Text)

Max Activating Token Index: 344

Text #16

Max Range: 4.2699. Min Range: -4.2699

Max Act: 4.0214. Min Act: -0.1700

Data Index: 4026611 (Open Web Text)

Max Activating Token Index: 211

Text #17

Max Range: 4.2699. Min Range: -4.2699

Max Act: 4.0413. Min Act: -0.1700

Data Index: 384696 (Open Web Text)

Max Activating Token Index: 400

Text #18

Max Range: 4.2699. Min Range: -4.2699

Max Act: 3.9927. Min Act: -0.1700

Data Index: 2779321 (Open Web Text)

Max Activating Token Index: 1003

Text #19

Max Range: 4.2699. Min Range: -4.2699

Max Act: 4.0240. Min Act: -0.1700

Data Index: 3063143 (Open Web Text)

Max Activating Token Index: 486