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

Dataset: Open Web Text

Neuron 1171 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: 4.1988. Min Range: -4.1988

Max Act: 4.1988. Min Act: -0.1700

Data Index: 4164377 (Open Web Text)

Max Activating Token Index: 397

Text #1

Max Range: 4.1988. Min Range: -4.1988

Max Act: 4.1548. Min Act: -0.1700

Data Index: 1166898 (Open Web Text)

Max Activating Token Index: 349

Text #2

Max Range: 4.1988. Min Range: -4.1988

Max Act: 4.1088. Min Act: -0.1700

Data Index: 5336964 (Open Web Text)

Max Activating Token Index: 744

Text #3

Max Range: 4.1988. Min Range: -4.1988

Max Act: 4.1428. Min Act: -0.1700

Data Index: 2502227 (Open Web Text)

Max Activating Token Index: 690

Text #4

Max Range: 4.1988. Min Range: -4.1988

Max Act: 4.1073. Min Act: -0.1700

Data Index: 1757171 (Open Web Text)

Max Activating Token Index: 266

Text #5

Max Range: 4.1988. Min Range: -4.1988

Max Act: 4.1116. Min Act: -0.1700

Data Index: 7711630 (Open Web Text)

Max Activating Token Index: 612

Text #6

Max Range: 4.1988. Min Range: -4.1988

Max Act: 4.0971. Min Act: -0.1700

Data Index: 7230110 (Open Web Text)

Max Activating Token Index: 432

Text #7

Max Range: 4.1988. Min Range: -4.1988

Max Act: 4.0795. Min Act: -0.1700

Data Index: 8677034 (Open Web Text)

Max Activating Token Index: 332

Text #8

Max Range: 4.1988. Min Range: -4.1988

Max Act: 4.0722. Min Act: -0.1700

Data Index: 8021506 (Open Web Text)

Max Activating Token Index: 247

Text #9

Max Range: 4.1988. Min Range: -4.1988

Max Act: 4.0668. Min Act: -0.1700

Data Index: 7881671 (Open Web Text)

Max Activating Token Index: 1008

Text #10

Max Range: 4.1988. Min Range: -4.1988

Max Act: 4.0558. Min Act: -0.1700

Data Index: 4044775 (Open Web Text)

Max Activating Token Index: 553

Text #11

Max Range: 4.1988. Min Range: -4.1988

Max Act: 4.0494. Min Act: -0.1700

Data Index: 6024115 (Open Web Text)

Max Activating Token Index: 492

Text #12

Max Range: 4.1988. Min Range: -4.1988

Max Act: 4.0521. Min Act: -0.1700

Data Index: 6455565 (Open Web Text)

Max Activating Token Index: 282

Text #13

Max Range: 4.1988. Min Range: -4.1988

Max Act: 4.0403. Min Act: -0.1700

Data Index: 2851199 (Open Web Text)

Max Activating Token Index: 86

Text #14

Max Range: 4.1988. Min Range: -4.1988

Max Act: 4.0250. Min Act: -0.1700

Data Index: 687268 (Open Web Text)

Max Activating Token Index: 916

Text #15

Max Range: 4.1988. Min Range: -4.1988

Max Act: 4.0343. Min Act: -0.1700

Data Index: 2538040 (Open Web Text)

Max Activating Token Index: 197

Text #16

Max Range: 4.1988. Min Range: -4.1988

Max Act: 4.0116. Min Act: -0.1700

Data Index: 2851195 (Open Web Text)

Max Activating Token Index: 849

Text #17

Max Range: 4.1988. Min Range: -4.1988

Max Act: 3.9959. Min Act: -0.1700

Data Index: 5520236 (Open Web Text)

Max Activating Token Index: 548

Text #18

Max Range: 4.1988. Min Range: -4.1988

Max Act: 4.0183. Min Act: -0.1700

Data Index: 729699 (Open Web Text)

Max Activating Token Index: 772

Text #19

Max Range: 4.1988. Min Range: -4.1988

Max Act: 4.0288. Min Act: -0.1700

Data Index: 7909943 (Open Web Text)

Max Activating Token Index: 772