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

Dataset: Open Web Text

Neuron 344 in Layer 5

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: 4.0856. Min Range: -4.0856

Max Act: 4.0856. Min Act: -0.1700

Data Index: 835042 (Open Web Text)

Max Activating Token Index: 930

Text #1

Max Range: 4.0856. Min Range: -4.0856

Max Act: 4.0310. Min Act: -0.1700

Data Index: 8576159 (Open Web Text)

Max Activating Token Index: 214

Text #2

Max Range: 4.0856. Min Range: -4.0856

Max Act: 3.9396. Min Act: -0.1700

Data Index: 8713612 (Open Web Text)

Max Activating Token Index: 390

Text #3

Max Range: 4.0856. Min Range: -4.0856

Max Act: 3.9325. Min Act: -0.1700

Data Index: 4814433 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 4.0856. Min Range: -4.0856

Max Act: 3.8463. Min Act: -0.1700

Data Index: 7928735 (Open Web Text)

Max Activating Token Index: 676

Text #5

Max Range: 4.0856. Min Range: -4.0856

Max Act: 3.9050. Min Act: -0.1700

Data Index: 633244 (Open Web Text)

Max Activating Token Index: 460

Text #6

Max Range: 4.0856. Min Range: -4.0856

Max Act: 3.8254. Min Act: -0.1700

Data Index: 684820 (Open Web Text)

Max Activating Token Index: 469

Text #7

Max Range: 4.0856. Min Range: -4.0856

Max Act: 3.7880. Min Act: -0.1700

Data Index: 2349261 (Open Web Text)

Max Activating Token Index: 653

Text #8

Max Range: 4.0856. Min Range: -4.0856

Max Act: 3.7895. Min Act: -0.1700

Data Index: 2513691 (Open Web Text)

Max Activating Token Index: 546

Text #9

Max Range: 4.0856. Min Range: -4.0856

Max Act: 3.7827. Min Act: -0.1700

Data Index: 5617181 (Open Web Text)

Max Activating Token Index: 978

Text #10

Max Range: 4.0856. Min Range: -4.0856

Max Act: 3.7672. Min Act: -0.1700

Data Index: 4790859 (Open Web Text)

Max Activating Token Index: 559

Text #11

Max Range: 4.0856. Min Range: -4.0856

Max Act: 3.7614. Min Act: -0.1700

Data Index: 7047292 (Open Web Text)

Max Activating Token Index: 252

Text #12

Max Range: 4.0856. Min Range: -4.0856

Max Act: 3.7697. Min Act: -0.1700

Data Index: 5993804 (Open Web Text)

Max Activating Token Index: 97

Text #13

Max Range: 4.0856. Min Range: -4.0856

Max Act: 3.7802. Min Act: -0.1700

Data Index: 1693106 (Open Web Text)

Max Activating Token Index: 423

Text #14

Max Range: 4.0856. Min Range: -4.0856

Max Act: 3.7354. Min Act: -0.1700

Data Index: 576957 (Open Web Text)

Max Activating Token Index: 78

Text #15

Max Range: 4.0856. Min Range: -4.0856

Max Act: 3.7412. Min Act: -0.1700

Data Index: 4819544 (Open Web Text)

Max Activating Token Index: 477

Text #16

Max Range: 4.0856. Min Range: -4.0856

Max Act: 3.7215. Min Act: -0.1700

Data Index: 4529386 (Open Web Text)

Max Activating Token Index: 439

Text #17

Max Range: 4.0856. Min Range: -4.0856

Max Act: 3.7427. Min Act: -0.1700

Data Index: 6816606 (Open Web Text)

Max Activating Token Index: 685

Text #18

Max Range: 4.0856. Min Range: -4.0856

Max Act: 3.7287. Min Act: -0.1700

Data Index: 4393415 (Open Web Text)

Max Activating Token Index: 201

Text #19

Max Range: 4.0856. Min Range: -4.0856

Max Act: 3.7048. Min Act: -0.1700

Data Index: 5815447 (Open Web Text)

Max Activating Token Index: 570