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

Dataset: Open Web Text

Neuron 2346 in Layer 4

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: 3.2665. Min Range: -3.2665

Max Act: 3.2665. Min Act: -0.1700

Data Index: 1681964 (Open Web Text)

Max Activating Token Index: 127

Text #1

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.1860. Min Act: -0.1700

Data Index: 2738498 (Open Web Text)

Max Activating Token Index: 596

Text #2

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.1275. Min Act: -0.1700

Data Index: 6486623 (Open Web Text)

Max Activating Token Index: 809

Text #3

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.0723. Min Act: -0.1700

Data Index: 4782112 (Open Web Text)

Max Activating Token Index: 28

Text #4

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.0797. Min Act: -0.1700

Data Index: 3722997 (Open Web Text)

Max Activating Token Index: 596

Text #5

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.0909. Min Act: -0.1700

Data Index: 7535551 (Open Web Text)

Max Activating Token Index: 743

Text #6

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.0542. Min Act: -0.1700

Data Index: 2666606 (Open Web Text)

Max Activating Token Index: 727

Text #7

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.9952. Min Act: -0.1700

Data Index: 2881946 (Open Web Text)

Max Activating Token Index: 648

Text #8

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.9813. Min Act: -0.1700

Data Index: 5882238 (Open Web Text)

Max Activating Token Index: 384

Text #9

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.9537. Min Act: -0.1700

Data Index: 8772205 (Open Web Text)

Max Activating Token Index: 598

Text #10

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.9802. Min Act: -0.1700

Data Index: 7228089 (Open Web Text)

Max Activating Token Index: 454

Text #11

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.9538. Min Act: -0.1700

Data Index: 5831305 (Open Web Text)

Max Activating Token Index: 663

Text #12

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.9500. Min Act: -0.1700

Data Index: 1972734 (Open Web Text)

Max Activating Token Index: 24

Text #13

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.9559. Min Act: -0.1700

Data Index: 6463485 (Open Web Text)

Max Activating Token Index: 304

Text #14

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.9325. Min Act: -0.1700

Data Index: 1249631 (Open Web Text)

Max Activating Token Index: 394

Text #15

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.9337. Min Act: -0.1700

Data Index: 4226243 (Open Web Text)

Max Activating Token Index: 424

Text #16

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.9234. Min Act: -0.1700

Data Index: 6984501 (Open Web Text)

Max Activating Token Index: 581

Text #17

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.9080. Min Act: -0.1700

Data Index: 2492182 (Open Web Text)

Max Activating Token Index: 538

Text #18

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.9202. Min Act: -0.1700

Data Index: 6171482 (Open Web Text)

Max Activating Token Index: 139

Text #19

Max Range: 3.2665. Min Range: -3.2665

Max Act: 2.9320. Min Act: -0.1700

Data Index: 7623058 (Open Web Text)

Max Activating Token Index: 992