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

Dataset: Open Web Text

Neuron 1917 in Layer 6

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: 4.7711. Min Range: -4.7711

Max Act: 4.7711. Min Act: -0.1700

Data Index: 3301548 (Open Web Text)

Max Activating Token Index: 633

Text #1

Max Range: 4.7711. Min Range: -4.7711

Max Act: 4.7287. Min Act: -0.1700

Data Index: 1329628 (Open Web Text)

Max Activating Token Index: 67

Text #2

Max Range: 4.7711. Min Range: -4.7711

Max Act: 4.6402. Min Act: -0.1700

Data Index: 8667876 (Open Web Text)

Max Activating Token Index: 111

Text #3

Max Range: 4.7711. Min Range: -4.7711

Max Act: 4.6694. Min Act: -0.1700

Data Index: 4863276 (Open Web Text)

Max Activating Token Index: 941

Text #4

Max Range: 4.7711. Min Range: -4.7711

Max Act: 4.6766. Min Act: -0.1700

Data Index: 4794491 (Open Web Text)

Max Activating Token Index: 383

Text #5

Max Range: 4.7711. Min Range: -4.7711

Max Act: 4.6313. Min Act: -0.1700

Data Index: 1210056 (Open Web Text)

Max Activating Token Index: 210

Text #6

Max Range: 4.7711. Min Range: -4.7711

Max Act: 4.6691. Min Act: -0.1700

Data Index: 1412789 (Open Web Text)

Max Activating Token Index: 431

Text #7

Max Range: 4.7711. Min Range: -4.7711

Max Act: 4.5943. Min Act: -0.1700

Data Index: 6257710 (Open Web Text)

Max Activating Token Index: 903

Text #8

Max Range: 4.7711. Min Range: -4.7711

Max Act: 4.5945. Min Act: -0.1700

Data Index: 3033797 (Open Web Text)

Max Activating Token Index: 343

Text #9

Max Range: 4.7711. Min Range: -4.7711

Max Act: 4.5963. Min Act: -0.1700

Data Index: 2996852 (Open Web Text)

Max Activating Token Index: 425

Text #10

Max Range: 4.7711. Min Range: -4.7711

Max Act: 4.5984. Min Act: -0.1700

Data Index: 3328763 (Open Web Text)

Max Activating Token Index: 107

Text #11

Max Range: 4.7711. Min Range: -4.7711

Max Act: 4.5654. Min Act: -0.1700

Data Index: 4536685 (Open Web Text)

Max Activating Token Index: 181

Text #12

Max Range: 4.7711. Min Range: -4.7711

Max Act: 4.5839. Min Act: -0.1700

Data Index: 6596874 (Open Web Text)

Max Activating Token Index: 984

Text #13

Max Range: 4.7711. Min Range: -4.7711

Max Act: 4.5798. Min Act: -0.1700

Data Index: 3091587 (Open Web Text)

Max Activating Token Index: 344

Text #14

Max Range: 4.7711. Min Range: -4.7711

Max Act: 4.5416. Min Act: -0.1700

Data Index: 6012600 (Open Web Text)

Max Activating Token Index: 905

Text #15

Max Range: 4.7711. Min Range: -4.7711

Max Act: 4.5430. Min Act: -0.1700

Data Index: 2973468 (Open Web Text)

Max Activating Token Index: 913

Text #16

Max Range: 4.7711. Min Range: -4.7711

Max Act: 4.5243. Min Act: -0.1700

Data Index: 3541276 (Open Web Text)

Max Activating Token Index: 532

Text #17

Max Range: 4.7711. Min Range: -4.7711

Max Act: 4.5354. Min Act: -0.1700

Data Index: 2849670 (Open Web Text)

Max Activating Token Index: 614

Text #18

Max Range: 4.7711. Min Range: -4.7711

Max Act: 4.5488. Min Act: -0.1700

Data Index: 770820 (Open Web Text)

Max Activating Token Index: 437

Text #19

Max Range: 4.7711. Min Range: -4.7711

Max Act: 4.5327. Min Act: -0.1700

Data Index: 3558316 (Open Web Text)

Max Activating Token Index: 554