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

Dataset: Open Web Text

Neuron 1333 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: 3.4895. Min Range: -3.4895

Max Act: 3.4895. Min Act: -0.1700

Data Index: 8719437 (Open Web Text)

Max Activating Token Index: 82

Text #1

Max Range: 3.4895. Min Range: -3.4895

Max Act: 3.3671. Min Act: -0.1700

Data Index: 2890762 (Open Web Text)

Max Activating Token Index: 671

Text #2

Max Range: 3.4895. Min Range: -3.4895

Max Act: 3.3584. Min Act: -0.1700

Data Index: 8567845 (Open Web Text)

Max Activating Token Index: 524

Text #3

Max Range: 3.4895. Min Range: -3.4895

Max Act: 3.3228. Min Act: -0.1700

Data Index: 1498359 (Open Web Text)

Max Activating Token Index: 474

Text #4

Max Range: 3.4895. Min Range: -3.4895

Max Act: 3.2845. Min Act: -0.1700

Data Index: 5409732 (Open Web Text)

Max Activating Token Index: 551

Text #5

Max Range: 3.4895. Min Range: -3.4895

Max Act: 3.2477. Min Act: -0.1700

Data Index: 8153729 (Open Web Text)

Max Activating Token Index: 634

Text #6

Max Range: 3.4895. Min Range: -3.4895

Max Act: 3.2690. Min Act: -0.1700

Data Index: 699375 (Open Web Text)

Max Activating Token Index: 818

Text #7

Max Range: 3.4895. Min Range: -3.4895

Max Act: 3.2371. Min Act: -0.1700

Data Index: 1522498 (Open Web Text)

Max Activating Token Index: 445

Text #8

Max Range: 3.4895. Min Range: -3.4895

Max Act: 3.2375. Min Act: -0.1700

Data Index: 158878 (Open Web Text)

Max Activating Token Index: 73

Text #9

Max Range: 3.4895. Min Range: -3.4895

Max Act: 3.2248. Min Act: -0.1700

Data Index: 1579816 (Open Web Text)

Max Activating Token Index: 502

Text #10

Max Range: 3.4895. Min Range: -3.4895

Max Act: 3.2162. Min Act: -0.1700

Data Index: 4453012 (Open Web Text)

Max Activating Token Index: 116

Text #11

Max Range: 3.4895. Min Range: -3.4895

Max Act: 3.2331. Min Act: -0.1700

Data Index: 6741998 (Open Web Text)

Max Activating Token Index: 487

Text #12

Max Range: 3.4895. Min Range: -3.4895

Max Act: 3.2036. Min Act: -0.1700

Data Index: 1145191 (Open Web Text)

Max Activating Token Index: 901

Text #13

Max Range: 3.4895. Min Range: -3.4895

Max Act: 3.1896. Min Act: -0.1700

Data Index: 3732298 (Open Web Text)

Max Activating Token Index: 174

Text #14

Max Range: 3.4895. Min Range: -3.4895

Max Act: 3.1958. Min Act: -0.1700

Data Index: 8594023 (Open Web Text)

Max Activating Token Index: 705

Text #15

Max Range: 3.4895. Min Range: -3.4895

Max Act: 3.1823. Min Act: -0.1700

Data Index: 3607409 (Open Web Text)

Max Activating Token Index: 117

Text #16

Max Range: 3.4895. Min Range: -3.4895

Max Act: 3.1555. Min Act: -0.1700

Data Index: 3808925 (Open Web Text)

Max Activating Token Index: 81

Text #17

Max Range: 3.4895. Min Range: -3.4895

Max Act: 3.1602. Min Act: -0.1700

Data Index: 2878012 (Open Web Text)

Max Activating Token Index: 594

Text #18

Max Range: 3.4895. Min Range: -3.4895

Max Act: 3.1626. Min Act: -0.1700

Data Index: 4071267 (Open Web Text)

Max Activating Token Index: 978

Text #19

Max Range: 3.4895. Min Range: -3.4895

Max Act: 3.1576. Min Act: -0.1700

Data Index: 5690922 (Open Web Text)

Max Activating Token Index: 779