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

Dataset: Open Web Text

Neuron 814 in Layer 2

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: 5.4605. Min Range: -5.4605

Max Act: 5.4605. Min Act: -0.1700

Data Index: 6655622 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 5.4605. Min Range: -5.4605

Max Act: 5.3036. Min Act: -0.1700

Data Index: 5460707 (Open Web Text)

Max Activating Token Index: 389

Text #2

Max Range: 5.4605. Min Range: -5.4605

Max Act: 5.2933. Min Act: -0.1700

Data Index: 8760533 (Open Web Text)

Max Activating Token Index: 62

Text #3

Max Range: 5.4605. Min Range: -5.4605

Max Act: 5.2444. Min Act: -0.1700

Data Index: 3051888 (Open Web Text)

Max Activating Token Index: 124

Text #4

Max Range: 5.4605. Min Range: -5.4605

Max Act: 5.2411. Min Act: -0.1697

Data Index: 5285407 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 5.4605. Min Range: -5.4605

Max Act: 5.2368. Min Act: -0.1700

Data Index: 288087 (Open Web Text)

Max Activating Token Index: 64

Text #6

Max Range: 5.4605. Min Range: -5.4605

Max Act: 5.2111. Min Act: -0.1699

Data Index: 4132527 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 5.4605. Min Range: -5.4605

Max Act: 5.2200. Min Act: -0.1700

Data Index: 7015700 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 5.4605. Min Range: -5.4605

Max Act: 5.1800. Min Act: -0.1700

Data Index: 3051876 (Open Web Text)

Max Activating Token Index: 111

Text #9

Max Range: 5.4605. Min Range: -5.4605

Max Act: 5.2172. Min Act: -0.1700

Data Index: 2584662 (Open Web Text)

Max Activating Token Index: 184

Text #10

Max Range: 5.4605. Min Range: -5.4605

Max Act: 5.1937. Min Act: -0.1700

Data Index: 2607888 (Open Web Text)

Max Activating Token Index: 80

Text #11

Max Range: 5.4605. Min Range: -5.4605

Max Act: 5.1610. Min Act: -0.1696

Data Index: 779517 (Open Web Text)

Max Activating Token Index: 613

Text #12

Max Range: 5.4605. Min Range: -5.4605

Max Act: 5.1941. Min Act: -0.1700

Data Index: 6064595 (Open Web Text)

Max Activating Token Index: 25

Text #13

Max Range: 5.4605. Min Range: -5.4605

Max Act: 5.2064. Min Act: -0.1700

Data Index: 779520 (Open Web Text)

Max Activating Token Index: 89

Text #14

Max Range: 5.4605. Min Range: -5.4605

Max Act: 5.1959. Min Act: -0.1700

Data Index: 3354310 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.4605. Min Range: -5.4605

Max Act: 5.1222. Min Act: -0.1700

Data Index: 1819646 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.4605. Min Range: -5.4605

Max Act: 5.1417. Min Act: -0.1700

Data Index: 2788070 (Open Web Text)

Max Activating Token Index: 990

Text #17

Max Range: 5.4605. Min Range: -5.4605

Max Act: 5.1103. Min Act: -0.1697

Data Index: 2856537 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 5.4605. Min Range: -5.4605

Max Act: 5.1101. Min Act: -0.1700

Data Index: 6025938 (Open Web Text)

Max Activating Token Index: 647

Text #19

Max Range: 5.4605. Min Range: -5.4605

Max Act: 5.1278. Min Act: -0.1700

Data Index: 5537770 (Open Web Text)

Max Activating Token Index: 12