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

Dataset: Open Web Text

Neuron 2232 in Layer 0

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: 4.4386. Min Range: -4.4386

Max Act: 4.4386. Min Act: -0.1700

Data Index: 646171 (Open Web Text)

Max Activating Token Index: 84

Text #1

Max Range: 4.4386. Min Range: -4.4386

Max Act: 4.4280. Min Act: -0.1700

Data Index: 249366 (Open Web Text)

Max Activating Token Index: 46

Text #2

Max Range: 4.4386. Min Range: -4.4386

Max Act: 4.3938. Min Act: -0.1700

Data Index: 6858783 (Open Web Text)

Max Activating Token Index: 31

Text #3

Max Range: 4.4386. Min Range: -4.4386

Max Act: 4.3568. Min Act: -0.1700

Data Index: 2652439 (Open Web Text)

Max Activating Token Index: 389

Text #4

Max Range: 4.4386. Min Range: -4.4386

Max Act: 4.3522. Min Act: -0.1700

Data Index: 7583087 (Open Web Text)

Max Activating Token Index: 694

Text #5

Max Range: 4.4386. Min Range: -4.4386

Max Act: 4.3287. Min Act: -0.1700

Data Index: 652973 (Open Web Text)

Max Activating Token Index: 316

Text #6

Max Range: 4.4386. Min Range: -4.4386

Max Act: 4.3263. Min Act: -0.1700

Data Index: 2568569 (Open Web Text)

Max Activating Token Index: 41

Text #7

Max Range: 4.4386. Min Range: -4.4386

Max Act: 4.3370. Min Act: -0.1700

Data Index: 8191612 (Open Web Text)

Max Activating Token Index: 697

Text #8

Max Range: 4.4386. Min Range: -4.4386

Max Act: 4.2790. Min Act: -0.1700

Data Index: 551638 (Open Web Text)

Max Activating Token Index: 227

Text #9

Max Range: 4.4386. Min Range: -4.4386

Max Act: 4.2802. Min Act: -0.1700

Data Index: 3083418 (Open Web Text)

Max Activating Token Index: 55

Text #10

Max Range: 4.4386. Min Range: -4.4386

Max Act: 4.2711. Min Act: -0.1700

Data Index: 2229834 (Open Web Text)

Max Activating Token Index: 297

Text #11

Max Range: 4.4386. Min Range: -4.4386

Max Act: 4.2760. Min Act: -0.1700

Data Index: 6137957 (Open Web Text)

Max Activating Token Index: 95

Text #12

Max Range: 4.4386. Min Range: -4.4386

Max Act: 4.2810. Min Act: -0.1700

Data Index: 1184373 (Open Web Text)

Max Activating Token Index: 184

Text #13

Max Range: 4.4386. Min Range: -4.4386

Max Act: 4.2959. Min Act: -0.1700

Data Index: 4317021 (Open Web Text)

Max Activating Token Index: 724

Text #14

Max Range: 4.4386. Min Range: -4.4386

Max Act: 4.2908. Min Act: -0.1700

Data Index: 4262039 (Open Web Text)

Max Activating Token Index: 275

Text #15

Max Range: 4.4386. Min Range: -4.4386

Max Act: 4.2936. Min Act: -0.1700

Data Index: 1632938 (Open Web Text)

Max Activating Token Index: 153

Text #16

Max Range: 4.4386. Min Range: -4.4386

Max Act: 4.2913. Min Act: -0.1700

Data Index: 4829342 (Open Web Text)

Max Activating Token Index: 69

Text #17

Max Range: 4.4386. Min Range: -4.4386

Max Act: 4.2892. Min Act: -0.1700

Data Index: 5286462 (Open Web Text)

Max Activating Token Index: 633

Text #18

Max Range: 4.4386. Min Range: -4.4386

Max Act: 4.2823. Min Act: -0.1700

Data Index: 5345490 (Open Web Text)

Max Activating Token Index: 828

Text #19

Max Range: 4.4386. Min Range: -4.4386

Max Act: 4.2933. Min Act: -0.1700

Data Index: 3351744 (Open Web Text)

Max Activating Token Index: 315