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

Dataset: Open Web Text

Neuron 736 in Layer 2

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: 4.0342. Min Range: -4.0342

Max Act: 4.0342. Min Act: -0.1700

Data Index: 7272486 (Open Web Text)

Max Activating Token Index: 97

Text #1

Max Range: 4.0342. Min Range: -4.0342

Max Act: 4.0069. Min Act: -0.1700

Data Index: 897052 (Open Web Text)

Max Activating Token Index: 71

Text #2

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.9742. Min Act: -0.1700

Data Index: 5249454 (Open Web Text)

Max Activating Token Index: 404

Text #3

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.9451. Min Act: -0.1700

Data Index: 4207337 (Open Web Text)

Max Activating Token Index: 433

Text #4

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.9506. Min Act: -0.1700

Data Index: 2381385 (Open Web Text)

Max Activating Token Index: 614

Text #5

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.9415. Min Act: -0.1700

Data Index: 1112442 (Open Web Text)

Max Activating Token Index: 332

Text #6

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.9196. Min Act: -0.1700

Data Index: 6991262 (Open Web Text)

Max Activating Token Index: 964

Text #7

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.9343. Min Act: -0.1700

Data Index: 7311710 (Open Web Text)

Max Activating Token Index: 876

Text #8

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.9355. Min Act: -0.1700

Data Index: 1607773 (Open Web Text)

Max Activating Token Index: 439

Text #9

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.8649. Min Act: -0.1700

Data Index: 502537 (Open Web Text)

Max Activating Token Index: 691

Text #10

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.9031. Min Act: -0.1700

Data Index: 4375918 (Open Web Text)

Max Activating Token Index: 581

Text #11

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.8775. Min Act: -0.1700

Data Index: 6592587 (Open Web Text)

Max Activating Token Index: 1009

Text #12

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.8918. Min Act: -0.1700

Data Index: 4221556 (Open Web Text)

Max Activating Token Index: 487

Text #13

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.8781. Min Act: -0.1700

Data Index: 8021829 (Open Web Text)

Max Activating Token Index: 445

Text #14

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.8678. Min Act: -0.1700

Data Index: 4600828 (Open Web Text)

Max Activating Token Index: 187

Text #15

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.8952. Min Act: -0.1700

Data Index: 6324309 (Open Web Text)

Max Activating Token Index: 723

Text #16

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.8769. Min Act: -0.1700

Data Index: 4158124 (Open Web Text)

Max Activating Token Index: 162

Text #17

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.8717. Min Act: -0.1700

Data Index: 5286858 (Open Web Text)

Max Activating Token Index: 958

Text #18

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.8682. Min Act: -0.1700

Data Index: 1660836 (Open Web Text)

Max Activating Token Index: 879

Text #19

Max Range: 4.0342. Min Range: -4.0342

Max Act: 3.8479. Min Act: -0.1700

Data Index: 4418302 (Open Web Text)

Max Activating Token Index: 607