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

Dataset: Open Web Text

Neuron 706 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: 4.7820. Min Range: -4.7820

Max Act: 4.7820. Min Act: -0.1700

Data Index: 350627 (Open Web Text)

Max Activating Token Index: 29

Text #1

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.5927. Min Act: -0.1700

Data Index: 7141431 (Open Web Text)

Max Activating Token Index: 503

Text #2

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.5925. Min Act: -0.1700

Data Index: 677643 (Open Web Text)

Max Activating Token Index: 180

Text #3

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.6287. Min Act: -0.1700

Data Index: 6275139 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.6089. Min Act: -0.1700

Data Index: 3646721 (Open Web Text)

Max Activating Token Index: 20

Text #5

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.5836. Min Act: -0.1700

Data Index: 6830299 (Open Web Text)

Max Activating Token Index: 1001

Text #6

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.5991. Min Act: -0.1700

Data Index: 8028144 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.5906. Min Act: -0.1700

Data Index: 4713686 (Open Web Text)

Max Activating Token Index: 161

Text #8

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.5821. Min Act: -0.1700

Data Index: 3429258 (Open Web Text)

Max Activating Token Index: 774

Text #9

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.5298. Min Act: -0.1700

Data Index: 6286100 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.5684. Min Act: -0.1700

Data Index: 4255417 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.5684. Min Act: -0.1700

Data Index: 6060484 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.5479. Min Act: -0.1700

Data Index: 3319328 (Open Web Text)

Max Activating Token Index: 807

Text #13

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.5529. Min Act: -0.1700

Data Index: 843733 (Open Web Text)

Max Activating Token Index: 567

Text #14

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.5446. Min Act: -0.1700

Data Index: 8629707 (Open Web Text)

Max Activating Token Index: 706

Text #15

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.5579. Min Act: -0.1700

Data Index: 3092561 (Open Web Text)

Max Activating Token Index: 327

Text #16

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.5437. Min Act: -0.1700

Data Index: 4634250 (Open Web Text)

Max Activating Token Index: 35

Text #17

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.5080. Min Act: -0.1700

Data Index: 4994019 (Open Web Text)

Max Activating Token Index: 385

Text #18

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.5467. Min Act: -0.1700

Data Index: 3429259 (Open Web Text)

Max Activating Token Index: 974

Text #19

Max Range: 4.7820. Min Range: -4.7820

Max Act: 4.5292. Min Act: -0.1700

Data Index: 1288841 (Open Web Text)

Max Activating Token Index: 48