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

Dataset: Open Web Text

Neuron 1950 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: 4.9889. Min Range: -4.9889

Max Act: 4.9889. Min Act: -0.1700

Data Index: 1999054 (Open Web Text)

Max Activating Token Index: 327

Text #1

Max Range: 4.9889. Min Range: -4.9889

Max Act: 4.6033. Min Act: -0.1700

Data Index: 4167655 (Open Web Text)

Max Activating Token Index: 285

Text #2

Max Range: 4.9889. Min Range: -4.9889

Max Act: 4.4546. Min Act: -0.1700

Data Index: 2581850 (Open Web Text)

Max Activating Token Index: 592

Text #3

Max Range: 4.9889. Min Range: -4.9889

Max Act: 4.4436. Min Act: -0.1700

Data Index: 1092409 (Open Web Text)

Max Activating Token Index: 725

Text #4

Max Range: 4.9889. Min Range: -4.9889

Max Act: 4.4144. Min Act: -0.1700

Data Index: 2358771 (Open Web Text)

Max Activating Token Index: 102

Text #5

Max Range: 4.9889. Min Range: -4.9889

Max Act: 4.3599. Min Act: -0.1700

Data Index: 7567701 (Open Web Text)

Max Activating Token Index: 165

Text #6

Max Range: 4.9889. Min Range: -4.9889

Max Act: 4.2888. Min Act: -0.1700

Data Index: 4532294 (Open Web Text)

Max Activating Token Index: 166

Text #7

Max Range: 4.9889. Min Range: -4.9889

Max Act: 4.3549. Min Act: -0.1700

Data Index: 5571164 (Open Web Text)

Max Activating Token Index: 673

Text #8

Max Range: 4.9889. Min Range: -4.9889

Max Act: 4.2914. Min Act: -0.1700

Data Index: 2504137 (Open Web Text)

Max Activating Token Index: 114

Text #9

Max Range: 4.9889. Min Range: -4.9889

Max Act: 4.2867. Min Act: -0.1700

Data Index: 94891 (Open Web Text)

Max Activating Token Index: 142

Text #10

Max Range: 4.9889. Min Range: -4.9889

Max Act: 4.2786. Min Act: -0.1700

Data Index: 1577361 (Open Web Text)

Max Activating Token Index: 533

Text #11

Max Range: 4.9889. Min Range: -4.9889

Max Act: 4.2704. Min Act: -0.1700

Data Index: 2130390 (Open Web Text)

Max Activating Token Index: 598

Text #12

Max Range: 4.9889. Min Range: -4.9889

Max Act: 4.3124. Min Act: -0.1700

Data Index: 8014444 (Open Web Text)

Max Activating Token Index: 665

Text #13

Max Range: 4.9889. Min Range: -4.9889

Max Act: 4.2795. Min Act: -0.1700

Data Index: 4107398 (Open Web Text)

Max Activating Token Index: 475

Text #14

Max Range: 4.9889. Min Range: -4.9889

Max Act: 4.2270. Min Act: -0.1700

Data Index: 7355654 (Open Web Text)

Max Activating Token Index: 525

Text #15

Max Range: 4.9889. Min Range: -4.9889

Max Act: 4.2483. Min Act: -0.1700

Data Index: 8682597 (Open Web Text)

Max Activating Token Index: 746

Text #16

Max Range: 4.9889. Min Range: -4.9889

Max Act: 4.2166. Min Act: -0.1700

Data Index: 265189 (Open Web Text)

Max Activating Token Index: 940

Text #17

Max Range: 4.9889. Min Range: -4.9889

Max Act: 4.1541. Min Act: -0.1700

Data Index: 2330698 (Open Web Text)

Max Activating Token Index: 506

Text #18

Max Range: 4.9889. Min Range: -4.9889

Max Act: 4.1637. Min Act: -0.1700

Data Index: 3359949 (Open Web Text)

Max Activating Token Index: 29

Text #19

Max Range: 4.9889. Min Range: -4.9889

Max Act: 4.1631. Min Act: -0.1700

Data Index: 1669653 (Open Web Text)

Max Activating Token Index: 637