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

Dataset: Open Web Text

Neuron 2460 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: 3.1380. Min Range: -3.1380

Max Act: 3.1380. Min Act: -0.1700

Data Index: 297132 (Open Web Text)

Max Activating Token Index: 865

Text #1

Max Range: 3.1380. Min Range: -3.1380

Max Act: 3.0381. Min Act: -0.1700

Data Index: 4924700 (Open Web Text)

Max Activating Token Index: 954

Text #2

Max Range: 3.1380. Min Range: -3.1380

Max Act: 3.0181. Min Act: -0.1700

Data Index: 8540164 (Open Web Text)

Max Activating Token Index: 640

Text #3

Max Range: 3.1380. Min Range: -3.1380

Max Act: 3.0034. Min Act: -0.1700

Data Index: 7765624 (Open Web Text)

Max Activating Token Index: 858

Text #4

Max Range: 3.1380. Min Range: -3.1380

Max Act: 3.0096. Min Act: -0.1700

Data Index: 772600 (Open Web Text)

Max Activating Token Index: 295

Text #5

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.9727. Min Act: -0.1700

Data Index: 2001263 (Open Web Text)

Max Activating Token Index: 661

Text #6

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.9455. Min Act: -0.1700

Data Index: 645498 (Open Web Text)

Max Activating Token Index: 823

Text #7

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.9250. Min Act: -0.1700

Data Index: 8390569 (Open Web Text)

Max Activating Token Index: 367

Text #8

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.8664. Min Act: -0.1700

Data Index: 6340526 (Open Web Text)

Max Activating Token Index: 282

Text #9

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.8662. Min Act: -0.1700

Data Index: 5516018 (Open Web Text)

Max Activating Token Index: 904

Text #10

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.8771. Min Act: -0.1700

Data Index: 1912167 (Open Web Text)

Max Activating Token Index: 935

Text #11

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.8714. Min Act: -0.1700

Data Index: 2764490 (Open Web Text)

Max Activating Token Index: 220

Text #12

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.8827. Min Act: -0.1700

Data Index: 8229402 (Open Web Text)

Max Activating Token Index: 535

Text #13

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.8642. Min Act: -0.1700

Data Index: 8569398 (Open Web Text)

Max Activating Token Index: 957

Text #14

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.8429. Min Act: -0.1700

Data Index: 897775 (Open Web Text)

Max Activating Token Index: 859

Text #15

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.8741. Min Act: -0.1700

Data Index: 6564387 (Open Web Text)

Max Activating Token Index: 158

Text #16

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.8393. Min Act: -0.1700

Data Index: 4853834 (Open Web Text)

Max Activating Token Index: 399

Text #17

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.8444. Min Act: -0.1700

Data Index: 3515907 (Open Web Text)

Max Activating Token Index: 762

Text #18

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.8458. Min Act: -0.1700

Data Index: 3239845 (Open Web Text)

Max Activating Token Index: 731

Text #19

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.8412. Min Act: -0.1700

Data Index: 7599629 (Open Web Text)

Max Activating Token Index: 632