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

Dataset: Open Web Text

Neuron 1021 in Layer 5

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: 4.2519. Min Range: -4.2519

Max Act: 4.2519. Min Act: -0.1700

Data Index: 5182934 (Open Web Text)

Max Activating Token Index: 248

Text #1

Max Range: 4.2519. Min Range: -4.2519

Max Act: 4.1168. Min Act: -0.1700

Data Index: 8425310 (Open Web Text)

Max Activating Token Index: 988

Text #2

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.9288. Min Act: -0.1700

Data Index: 6366663 (Open Web Text)

Max Activating Token Index: 666

Text #3

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.8503. Min Act: -0.1700

Data Index: 5762385 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.8054. Min Act: -0.1700

Data Index: 5432280 (Open Web Text)

Max Activating Token Index: 831

Text #5

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.7235. Min Act: -0.1700

Data Index: 7352622 (Open Web Text)

Max Activating Token Index: 617

Text #6

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.7494. Min Act: -0.1700

Data Index: 4740665 (Open Web Text)

Max Activating Token Index: 22

Text #7

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.6841. Min Act: -0.1699

Data Index: 8058957 (Open Web Text)

Max Activating Token Index: 328

Text #8

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.6545. Min Act: -0.1700

Data Index: 6070193 (Open Web Text)

Max Activating Token Index: 20

Text #9

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.3818. Min Act: -0.1700

Data Index: 6815495 (Open Web Text)

Max Activating Token Index: 381

Text #10

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.5470. Min Act: -0.1700

Data Index: 7830705 (Open Web Text)

Max Activating Token Index: 526

Text #11

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.5836. Min Act: -0.1700

Data Index: 3857781 (Open Web Text)

Max Activating Token Index: 15

Text #12

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.5214. Min Act: -0.1700

Data Index: 1394278 (Open Web Text)

Max Activating Token Index: 321

Text #13

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.4883. Min Act: -0.1700

Data Index: 7294782 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.3790. Min Act: -0.1700

Data Index: 682521 (Open Web Text)

Max Activating Token Index: 169

Text #15

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.4435. Min Act: -0.1700

Data Index: 290806 (Open Web Text)

Max Activating Token Index: 19

Text #16

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.4234. Min Act: -0.1691

Data Index: 2005541 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.3653. Min Act: -0.1700

Data Index: 7719450 (Open Web Text)

Max Activating Token Index: 96

Text #18

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.3235. Min Act: -0.1700

Data Index: 8579185 (Open Web Text)

Max Activating Token Index: 900

Text #19

Max Range: 4.2519. Min Range: -4.2519

Max Act: 3.3329. Min Act: -0.1700

Data Index: 136569 (Open Web Text)

Max Activating Token Index: 165