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

Dataset: Open Web Text

Neuron 533 in Layer 0

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: 5.7825. Min Range: -5.7825

Max Act: 5.7809. Min Act: -0.1700

Data Index: 7451222 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.7825. Min Act: -0.1700

Data Index: 1353440 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.7789. Min Act: -0.1700

Data Index: 6607577 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.7789. Min Act: -0.1700

Data Index: 371660 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.7809. Min Act: -0.1700

Data Index: 827681 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.7614. Min Act: -0.1700

Data Index: 8754291 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.7432. Min Act: -0.1700

Data Index: 8603017 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.6731. Min Act: -0.1700

Data Index: 1566848 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.6684. Min Act: -0.1700

Data Index: 4620475 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.6405. Min Act: -0.1700

Data Index: 4609060 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.6405. Min Act: -0.1700

Data Index: 2130253 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.5884. Min Act: -0.1700

Data Index: 3697158 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.6040. Min Act: -0.1700

Data Index: 7424609 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.5889. Min Act: -0.1700

Data Index: 8279457 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.5815. Min Act: -0.1700

Data Index: 928916 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.5667. Min Act: -0.1700

Data Index: 5623018 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.5831. Min Act: -0.1700

Data Index: 8109755 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.5831. Min Act: -0.1700

Data Index: 2998427 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.5785. Min Act: -0.1700

Data Index: 6010951 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.5745. Min Act: -0.1700

Data Index: 3138939 (Open Web Text)

Max Activating Token Index: 8