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

Dataset: Open Web Text

Neuron 1451 in Layer 1

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: 3.3675. Min Range: -3.3675

Max Act: 3.3675. Min Act: -0.1700

Data Index: 4335119 (Open Web Text)

Max Activating Token Index: 427

Text #1

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.3479. Min Act: -0.1700

Data Index: 3964469 (Open Web Text)

Max Activating Token Index: 235

Text #2

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.3502. Min Act: -0.1700

Data Index: 7610470 (Open Web Text)

Max Activating Token Index: 330

Text #3

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.3257. Min Act: -0.1700

Data Index: 2619419 (Open Web Text)

Max Activating Token Index: 397

Text #4

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.3400. Min Act: -0.1700

Data Index: 5914321 (Open Web Text)

Max Activating Token Index: 471

Text #5

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.2933. Min Act: -0.1700

Data Index: 4760266 (Open Web Text)

Max Activating Token Index: 927

Text #6

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.3058. Min Act: -0.1700

Data Index: 6097943 (Open Web Text)

Max Activating Token Index: 802

Text #7

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.2879. Min Act: -0.1700

Data Index: 3854068 (Open Web Text)

Max Activating Token Index: 400

Text #8

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.2886. Min Act: -0.1700

Data Index: 2261453 (Open Web Text)

Max Activating Token Index: 422

Text #9

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.2853. Min Act: -0.1700

Data Index: 8360267 (Open Web Text)

Max Activating Token Index: 483

Text #10

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.2836. Min Act: -0.1700

Data Index: 6743541 (Open Web Text)

Max Activating Token Index: 500

Text #11

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.2803. Min Act: -0.1700

Data Index: 2493075 (Open Web Text)

Max Activating Token Index: 614

Text #12

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.2773. Min Act: -0.1700

Data Index: 3031260 (Open Web Text)

Max Activating Token Index: 120

Text #13

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.2699. Min Act: -0.1700

Data Index: 60540 (Open Web Text)

Max Activating Token Index: 775

Text #14

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.2703. Min Act: -0.1700

Data Index: 2915593 (Open Web Text)

Max Activating Token Index: 71

Text #15

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.2709. Min Act: -0.1700

Data Index: 7759763 (Open Web Text)

Max Activating Token Index: 767

Text #16

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.2595. Min Act: -0.1700

Data Index: 6220205 (Open Web Text)

Max Activating Token Index: 197

Text #17

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.2606. Min Act: -0.1700

Data Index: 912573 (Open Web Text)

Max Activating Token Index: 487

Text #18

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.2496. Min Act: -0.1700

Data Index: 2947704 (Open Web Text)

Max Activating Token Index: 428

Text #19

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.2658. Min Act: -0.1700

Data Index: 5876056 (Open Web Text)

Max Activating Token Index: 414