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

Dataset: Open Web Text

Neuron 1231 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: 3.6463. Min Range: -3.6463

Max Act: 3.6463. Min Act: -0.1700

Data Index: 1345548 (Open Web Text)

Max Activating Token Index: 944

Text #1

Max Range: 3.6463. Min Range: -3.6463

Max Act: 3.5511. Min Act: -0.1700

Data Index: 8051773 (Open Web Text)

Max Activating Token Index: 551

Text #2

Max Range: 3.6463. Min Range: -3.6463

Max Act: 3.5612. Min Act: -0.1700

Data Index: 3418703 (Open Web Text)

Max Activating Token Index: 86

Text #3

Max Range: 3.6463. Min Range: -3.6463

Max Act: 3.5557. Min Act: -0.1700

Data Index: 3436218 (Open Web Text)

Max Activating Token Index: 929

Text #4

Max Range: 3.6463. Min Range: -3.6463

Max Act: 3.5305. Min Act: -0.1700

Data Index: 4165194 (Open Web Text)

Max Activating Token Index: 555

Text #5

Max Range: 3.6463. Min Range: -3.6463

Max Act: 3.5125. Min Act: -0.1700

Data Index: 2112480 (Open Web Text)

Max Activating Token Index: 555

Text #6

Max Range: 3.6463. Min Range: -3.6463

Max Act: 3.5180. Min Act: -0.1700

Data Index: 3272146 (Open Web Text)

Max Activating Token Index: 477

Text #7

Max Range: 3.6463. Min Range: -3.6463

Max Act: 3.5192. Min Act: -0.1700

Data Index: 4185416 (Open Web Text)

Max Activating Token Index: 138

Text #8

Max Range: 3.6463. Min Range: -3.6463

Max Act: 3.5099. Min Act: -0.1700

Data Index: 8735840 (Open Web Text)

Max Activating Token Index: 823

Text #9

Max Range: 3.6463. Min Range: -3.6463

Max Act: 3.4835. Min Act: -0.1700

Data Index: 2065146 (Open Web Text)

Max Activating Token Index: 657

Text #10

Max Range: 3.6463. Min Range: -3.6463

Max Act: 3.4782. Min Act: -0.1700

Data Index: 5682696 (Open Web Text)

Max Activating Token Index: 365

Text #11

Max Range: 3.6463. Min Range: -3.6463

Max Act: 3.4534. Min Act: -0.1700

Data Index: 1296779 (Open Web Text)

Max Activating Token Index: 225

Text #12

Max Range: 3.6463. Min Range: -3.6463

Max Act: 3.4614. Min Act: -0.1700

Data Index: 4357160 (Open Web Text)

Max Activating Token Index: 314

Text #13

Max Range: 3.6463. Min Range: -3.6463

Max Act: 3.4295. Min Act: -0.1700

Data Index: 3027288 (Open Web Text)

Max Activating Token Index: 910

Text #14

Max Range: 3.6463. Min Range: -3.6463

Max Act: 3.4519. Min Act: -0.1700

Data Index: 8327524 (Open Web Text)

Max Activating Token Index: 327

Text #15

Max Range: 3.6463. Min Range: -3.6463

Max Act: 3.4376. Min Act: -0.1700

Data Index: 1126116 (Open Web Text)

Max Activating Token Index: 965

Text #16

Max Range: 3.6463. Min Range: -3.6463

Max Act: 3.4392. Min Act: -0.1700

Data Index: 7512036 (Open Web Text)

Max Activating Token Index: 354

Text #17

Max Range: 3.6463. Min Range: -3.6463

Max Act: 3.4472. Min Act: -0.1700

Data Index: 7429131 (Open Web Text)

Max Activating Token Index: 257

Text #18

Max Range: 3.6463. Min Range: -3.6463

Max Act: 3.4246. Min Act: -0.1700

Data Index: 4402157 (Open Web Text)

Max Activating Token Index: 691

Text #19

Max Range: 3.6463. Min Range: -3.6463

Max Act: 3.4070. Min Act: -0.1700

Data Index: 5954413 (Open Web Text)

Max Activating Token Index: 899