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

Dataset: Open Web Text

Neuron 2734 in Layer 3

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: 4.0483. Min Range: -4.0483

Max Act: 4.0483. Min Act: -0.1700

Data Index: 7770039 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.0483. Min Range: -4.0483

Max Act: 4.0245. Min Act: -0.1700

Data Index: 5947632 (Open Web Text)

Max Activating Token Index: 383

Text #2

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.9631. Min Act: -0.1700

Data Index: 8173185 (Open Web Text)

Max Activating Token Index: 194

Text #3

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.9690. Min Act: -0.1700

Data Index: 2629264 (Open Web Text)

Max Activating Token Index: 441

Text #4

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.9593. Min Act: -0.1700

Data Index: 7213944 (Open Web Text)

Max Activating Token Index: 467

Text #5

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.9131. Min Act: -0.1700

Data Index: 8446939 (Open Web Text)

Max Activating Token Index: 160

Text #6

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.9020. Min Act: -0.1700

Data Index: 6259058 (Open Web Text)

Max Activating Token Index: 153

Text #7

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.9357. Min Act: -0.1700

Data Index: 8629684 (Open Web Text)

Max Activating Token Index: 217

Text #8

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.8866. Min Act: -0.1700

Data Index: 1669761 (Open Web Text)

Max Activating Token Index: 371

Text #9

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.8432. Min Act: -0.1700

Data Index: 1585804 (Open Web Text)

Max Activating Token Index: 296

Text #10

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.8625. Min Act: -0.1700

Data Index: 6617325 (Open Web Text)

Max Activating Token Index: 879

Text #11

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.8836. Min Act: -0.1700

Data Index: 280982 (Open Web Text)

Max Activating Token Index: 479

Text #12

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.9027. Min Act: -0.1700

Data Index: 1293888 (Open Web Text)

Max Activating Token Index: 681

Text #13

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.8707. Min Act: -0.1700

Data Index: 1602181 (Open Web Text)

Max Activating Token Index: 26

Text #14

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.8817. Min Act: -0.1700

Data Index: 7658327 (Open Web Text)

Max Activating Token Index: 644

Text #15

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.8888. Min Act: -0.1700

Data Index: 7662638 (Open Web Text)

Max Activating Token Index: 864

Text #16

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.8526. Min Act: -0.1700

Data Index: 1922707 (Open Web Text)

Max Activating Token Index: 741

Text #17

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.8406. Min Act: -0.1700

Data Index: 4649009 (Open Web Text)

Max Activating Token Index: 501

Text #18

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.8427. Min Act: -0.1700

Data Index: 1527986 (Open Web Text)

Max Activating Token Index: 546

Text #19

Max Range: 4.0483. Min Range: -4.0483

Max Act: 3.8189. Min Act: -0.1700

Data Index: 1235453 (Open Web Text)

Max Activating Token Index: 60