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

Dataset: Open Web Text

Neuron 397 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: 5.4268. Min Range: -5.4268

Max Act: 5.4268. Min Act: -0.1700

Data Index: 6778006 (Open Web Text)

Max Activating Token Index: 854

Text #1

Max Range: 5.4268. Min Range: -5.4268

Max Act: 5.2595. Min Act: -0.1700

Data Index: 1962783 (Open Web Text)

Max Activating Token Index: 929

Text #2

Max Range: 5.4268. Min Range: -5.4268

Max Act: 5.0829. Min Act: -0.1700

Data Index: 6274921 (Open Web Text)

Max Activating Token Index: 862

Text #3

Max Range: 5.4268. Min Range: -5.4268

Max Act: 4.9524. Min Act: -0.1700

Data Index: 6504671 (Open Web Text)

Max Activating Token Index: 578

Text #4

Max Range: 5.4268. Min Range: -5.4268

Max Act: 4.8950. Min Act: -0.1700

Data Index: 5834981 (Open Web Text)

Max Activating Token Index: 957

Text #5

Max Range: 5.4268. Min Range: -5.4268

Max Act: 4.8254. Min Act: -0.1700

Data Index: 3215360 (Open Web Text)

Max Activating Token Index: 101

Text #6

Max Range: 5.4268. Min Range: -5.4268

Max Act: 4.8387. Min Act: -0.1700

Data Index: 2106495 (Open Web Text)

Max Activating Token Index: 663

Text #7

Max Range: 5.4268. Min Range: -5.4268

Max Act: 4.8420. Min Act: -0.1700

Data Index: 622266 (Open Web Text)

Max Activating Token Index: 946

Text #8

Max Range: 5.4268. Min Range: -5.4268

Max Act: 4.7848. Min Act: -0.1700

Data Index: 5787364 (Open Web Text)

Max Activating Token Index: 538

Text #9

Max Range: 5.4268. Min Range: -5.4268

Max Act: 4.8385. Min Act: -0.1700

Data Index: 7139736 (Open Web Text)

Max Activating Token Index: 714

Text #10

Max Range: 5.4268. Min Range: -5.4268

Max Act: 4.8039. Min Act: -0.1700

Data Index: 8521148 (Open Web Text)

Max Activating Token Index: 475

Text #11

Max Range: 5.4268. Min Range: -5.4268

Max Act: 4.8063. Min Act: -0.1700

Data Index: 358578 (Open Web Text)

Max Activating Token Index: 49

Text #12

Max Range: 5.4268. Min Range: -5.4268

Max Act: 4.8056. Min Act: -0.1700

Data Index: 6464698 (Open Web Text)

Max Activating Token Index: 448

Text #13

Max Range: 5.4268. Min Range: -5.4268

Max Act: 4.8028. Min Act: -0.1700

Data Index: 4964464 (Open Web Text)

Max Activating Token Index: 640

Text #14

Max Range: 5.4268. Min Range: -5.4268

Max Act: 4.7709. Min Act: -0.1700

Data Index: 7000266 (Open Web Text)

Max Activating Token Index: 859

Text #15

Max Range: 5.4268. Min Range: -5.4268

Max Act: 4.7904. Min Act: -0.1700

Data Index: 4267723 (Open Web Text)

Max Activating Token Index: 96

Text #16

Max Range: 5.4268. Min Range: -5.4268

Max Act: 4.8019. Min Act: -0.1700

Data Index: 60925 (Open Web Text)

Max Activating Token Index: 357

Text #17

Max Range: 5.4268. Min Range: -5.4268

Max Act: 4.7635. Min Act: -0.1700

Data Index: 4175456 (Open Web Text)

Max Activating Token Index: 224

Text #18

Max Range: 5.4268. Min Range: -5.4268

Max Act: 4.7533. Min Act: -0.1700

Data Index: 379019 (Open Web Text)

Max Activating Token Index: 764

Text #19

Max Range: 5.4268. Min Range: -5.4268

Max Act: 4.7595. Min Act: -0.1700

Data Index: 6805856 (Open Web Text)

Max Activating Token Index: 610