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

Dataset: Open Web Text

Neuron 1869 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: 4.0227. Min Range: -4.0227

Max Act: 4.0227. Min Act: -0.1700

Data Index: 8817166 (Open Web Text)

Max Activating Token Index: 371

Text #1

Max Range: 4.0227. Min Range: -4.0227

Max Act: 3.8683. Min Act: -0.1700

Data Index: 72915 (Open Web Text)

Max Activating Token Index: 831

Text #2

Max Range: 4.0227. Min Range: -4.0227

Max Act: 3.8994. Min Act: -0.1700

Data Index: 5878764 (Open Web Text)

Max Activating Token Index: 670

Text #3

Max Range: 4.0227. Min Range: -4.0227

Max Act: 3.8894. Min Act: -0.1700

Data Index: 3595527 (Open Web Text)

Max Activating Token Index: 598

Text #4

Max Range: 4.0227. Min Range: -4.0227

Max Act: 3.8235. Min Act: -0.1700

Data Index: 1720470 (Open Web Text)

Max Activating Token Index: 490

Text #5

Max Range: 4.0227. Min Range: -4.0227

Max Act: 3.8019. Min Act: -0.1700

Data Index: 6168170 (Open Web Text)

Max Activating Token Index: 538

Text #6

Max Range: 4.0227. Min Range: -4.0227

Max Act: 3.8331. Min Act: -0.1700

Data Index: 2640217 (Open Web Text)

Max Activating Token Index: 494

Text #7

Max Range: 4.0227. Min Range: -4.0227

Max Act: 3.8314. Min Act: -0.1700

Data Index: 4964262 (Open Web Text)

Max Activating Token Index: 318

Text #8

Max Range: 4.0227. Min Range: -4.0227

Max Act: 3.8125. Min Act: -0.1700

Data Index: 2477515 (Open Web Text)

Max Activating Token Index: 282

Text #9

Max Range: 4.0227. Min Range: -4.0227

Max Act: 3.7842. Min Act: -0.1700

Data Index: 435363 (Open Web Text)

Max Activating Token Index: 319

Text #10

Max Range: 4.0227. Min Range: -4.0227

Max Act: 3.7680. Min Act: -0.1700

Data Index: 6394999 (Open Web Text)

Max Activating Token Index: 46

Text #11

Max Range: 4.0227. Min Range: -4.0227

Max Act: 3.8145. Min Act: -0.1700

Data Index: 3954103 (Open Web Text)

Max Activating Token Index: 537

Text #12

Max Range: 4.0227. Min Range: -4.0227

Max Act: 3.7646. Min Act: -0.1700

Data Index: 7310222 (Open Web Text)

Max Activating Token Index: 702

Text #13

Max Range: 4.0227. Min Range: -4.0227

Max Act: 3.7817. Min Act: -0.1700

Data Index: 3037387 (Open Web Text)

Max Activating Token Index: 237

Text #14

Max Range: 4.0227. Min Range: -4.0227

Max Act: 3.7783. Min Act: -0.1700

Data Index: 8499772 (Open Web Text)

Max Activating Token Index: 564

Text #15

Max Range: 4.0227. Min Range: -4.0227

Max Act: 3.7555. Min Act: -0.1700

Data Index: 3410628 (Open Web Text)

Max Activating Token Index: 200

Text #16

Max Range: 4.0227. Min Range: -4.0227

Max Act: 3.7133. Min Act: -0.1700

Data Index: 7971120 (Open Web Text)

Max Activating Token Index: 489

Text #17

Max Range: 4.0227. Min Range: -4.0227

Max Act: 3.7284. Min Act: -0.1700

Data Index: 7204927 (Open Web Text)

Max Activating Token Index: 735

Text #18

Max Range: 4.0227. Min Range: -4.0227

Max Act: 3.7853. Min Act: -0.1700

Data Index: 6759416 (Open Web Text)

Max Activating Token Index: 364

Text #19

Max Range: 4.0227. Min Range: -4.0227

Max Act: 3.7862. Min Act: -0.1700

Data Index: 2114507 (Open Web Text)

Max Activating Token Index: 590