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

Dataset: Open Web Text

Neuron 1509 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: 5.0088. Min Range: -5.0088

Max Act: 5.0088. Min Act: -0.1700

Data Index: 4223042 (Open Web Text)

Max Activating Token Index: 469

Text #1

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.9023. Min Act: -0.1700

Data Index: 7403030 (Open Web Text)

Max Activating Token Index: 839

Text #2

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.9122. Min Act: -0.1700

Data Index: 4598268 (Open Web Text)

Max Activating Token Index: 1010

Text #3

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.8680. Min Act: -0.1700

Data Index: 2232579 (Open Web Text)

Max Activating Token Index: 444

Text #4

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.8757. Min Act: -0.1700

Data Index: 2905577 (Open Web Text)

Max Activating Token Index: 989

Text #5

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.8865. Min Act: -0.1700

Data Index: 6261613 (Open Web Text)

Max Activating Token Index: 496

Text #6

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.8345. Min Act: -0.1700

Data Index: 4265255 (Open Web Text)

Max Activating Token Index: 820

Text #7

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.8456. Min Act: -0.1700

Data Index: 106826 (Open Web Text)

Max Activating Token Index: 381

Text #8

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.8517. Min Act: -0.1700

Data Index: 2055088 (Open Web Text)

Max Activating Token Index: 372

Text #9

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.8317. Min Act: -0.1700

Data Index: 1553412 (Open Web Text)

Max Activating Token Index: 631

Text #10

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.8417. Min Act: -0.1700

Data Index: 3426265 (Open Web Text)

Max Activating Token Index: 907

Text #11

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.7923. Min Act: -0.1700

Data Index: 8694973 (Open Web Text)

Max Activating Token Index: 638

Text #12

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.7980. Min Act: -0.1700

Data Index: 7656630 (Open Web Text)

Max Activating Token Index: 965

Text #13

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.8266. Min Act: -0.1700

Data Index: 8315581 (Open Web Text)

Max Activating Token Index: 635

Text #14

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.8032. Min Act: -0.1700

Data Index: 2468884 (Open Web Text)

Max Activating Token Index: 429

Text #15

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.8020. Min Act: -0.1700

Data Index: 4371457 (Open Web Text)

Max Activating Token Index: 25

Text #16

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.8255. Min Act: -0.1700

Data Index: 7674170 (Open Web Text)

Max Activating Token Index: 401

Text #17

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.7790. Min Act: -0.1700

Data Index: 6508120 (Open Web Text)

Max Activating Token Index: 557

Text #18

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.7566. Min Act: -0.1700

Data Index: 3904473 (Open Web Text)

Max Activating Token Index: 457

Text #19

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.7751. Min Act: -0.1700

Data Index: 2221504 (Open Web Text)

Max Activating Token Index: 427