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

Dataset: Open Web Text

Neuron 2975 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: 3.1776. Min Range: -3.1776

Max Act: 3.1776. Min Act: -0.1700

Data Index: 5676989 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.1776. Min Range: -3.1776

Max Act: 3.1761. Min Act: -0.1700

Data Index: 4160170 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.1776. Min Range: -3.1776

Max Act: 3.1605. Min Act: -0.1700

Data Index: 4700538 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.1776. Min Range: -3.1776

Max Act: 3.1462. Min Act: -0.1700

Data Index: 3850197 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.1776. Min Range: -3.1776

Max Act: 3.0949. Min Act: -0.1700

Data Index: 5934660 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 3.1776. Min Range: -3.1776

Max Act: 3.0835. Min Act: -0.1700

Data Index: 1659367 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.1776. Min Range: -3.1776

Max Act: 3.0656. Min Act: -0.1700

Data Index: 3508899 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.1776. Min Range: -3.1776

Max Act: 3.0461. Min Act: -0.1700

Data Index: 5665032 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 3.1776. Min Range: -3.1776

Max Act: 3.0528. Min Act: -0.1700

Data Index: 4919047 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.1776. Min Range: -3.1776

Max Act: 3.0352. Min Act: -0.1700

Data Index: 7814128 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.1776. Min Range: -3.1776

Max Act: 3.0332. Min Act: -0.1700

Data Index: 339261 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.1776. Min Range: -3.1776

Max Act: 3.0233. Min Act: -0.1700

Data Index: 5775555 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.1776. Min Range: -3.1776

Max Act: 3.0242. Min Act: -0.1700

Data Index: 8421367 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.1776. Min Range: -3.1776

Max Act: 3.0252. Min Act: -0.1700

Data Index: 7548347 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.1776. Min Range: -3.1776

Max Act: 3.0263. Min Act: -0.1700

Data Index: 3890691 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 3.1776. Min Range: -3.1776

Max Act: 3.0121. Min Act: -0.1700

Data Index: 7098952 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.1776. Min Range: -3.1776

Max Act: 3.0064. Min Act: -0.1700

Data Index: 3285774 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.1776. Min Range: -3.1776

Max Act: 3.0152. Min Act: -0.1700

Data Index: 1524865 (Open Web Text)

Max Activating Token Index: 108

Text #18

Max Range: 3.1776. Min Range: -3.1776

Max Act: 2.9935. Min Act: -0.1700

Data Index: 5178884 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.1776. Min Range: -3.1776

Max Act: 2.9852. Min Act: -0.1700

Data Index: 1076588 (Open Web Text)

Max Activating Token Index: 2