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

Dataset: Open Web Text

Neuron 2491 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: 4.2461. Min Range: -4.2461

Max Act: 4.2461. Min Act: -0.1700

Data Index: 2444820 (Open Web Text)

Max Activating Token Index: 277

Text #1

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.2449. Min Act: -0.1700

Data Index: 6518236 (Open Web Text)

Max Activating Token Index: 408

Text #2

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.1457. Min Act: -0.1700

Data Index: 3115084 (Open Web Text)

Max Activating Token Index: 429

Text #3

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.1312. Min Act: -0.1700

Data Index: 7854022 (Open Web Text)

Max Activating Token Index: 236

Text #4

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.1079. Min Act: -0.1700

Data Index: 5660972 (Open Web Text)

Max Activating Token Index: 166

Text #5

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.0935. Min Act: -0.1700

Data Index: 3000741 (Open Web Text)

Max Activating Token Index: 396

Text #6

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.0569. Min Act: -0.1700

Data Index: 340896 (Open Web Text)

Max Activating Token Index: 594

Text #7

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.1101. Min Act: -0.1700

Data Index: 7331712 (Open Web Text)

Max Activating Token Index: 23

Text #8

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.0608. Min Act: -0.1700

Data Index: 2032546 (Open Web Text)

Max Activating Token Index: 798

Text #9

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.0992. Min Act: -0.1700

Data Index: 1036306 (Open Web Text)

Max Activating Token Index: 441

Text #10

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.0548. Min Act: -0.1700

Data Index: 683576 (Open Web Text)

Max Activating Token Index: 484

Text #11

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.0306. Min Act: -0.1700

Data Index: 4402345 (Open Web Text)

Max Activating Token Index: 108

Text #12

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.0772. Min Act: -0.1700

Data Index: 2834787 (Open Web Text)

Max Activating Token Index: 1004

Text #13

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.0695. Min Act: -0.1700

Data Index: 6759982 (Open Web Text)

Max Activating Token Index: 592

Text #14

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.0346. Min Act: -0.1700

Data Index: 4257625 (Open Web Text)

Max Activating Token Index: 217

Text #15

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.0783. Min Act: -0.1700

Data Index: 4458267 (Open Web Text)

Max Activating Token Index: 309

Text #16

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.0268. Min Act: -0.1700

Data Index: 1390584 (Open Web Text)

Max Activating Token Index: 511

Text #17

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.0554. Min Act: -0.1700

Data Index: 3649172 (Open Web Text)

Max Activating Token Index: 264

Text #18

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.0453. Min Act: -0.1700

Data Index: 3189639 (Open Web Text)

Max Activating Token Index: 470

Text #19

Max Range: 4.2461. Min Range: -4.2461

Max Act: 4.0473. Min Act: -0.1700

Data Index: 8144478 (Open Web Text)

Max Activating Token Index: 1012