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

Dataset: Open Web Text

Neuron 1645 in Layer 1

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: 6.0652. Min Range: -6.0652

Max Act: 6.0652. Min Act: -0.1700

Data Index: 8233357 (Open Web Text)

Max Activating Token Index: 195

Text #1

Max Range: 6.0652. Min Range: -6.0652

Max Act: 5.9802. Min Act: -0.1700

Data Index: 3262413 (Open Web Text)

Max Activating Token Index: 154

Text #2

Max Range: 6.0652. Min Range: -6.0652

Max Act: 5.9390. Min Act: -0.1700

Data Index: 5561063 (Open Web Text)

Max Activating Token Index: 581

Text #3

Max Range: 6.0652. Min Range: -6.0652

Max Act: 5.8916. Min Act: -0.1700

Data Index: 6683075 (Open Web Text)

Max Activating Token Index: 119

Text #4

Max Range: 6.0652. Min Range: -6.0652

Max Act: 5.9022. Min Act: -0.1700

Data Index: 2176321 (Open Web Text)

Max Activating Token Index: 723

Text #5

Max Range: 6.0652. Min Range: -6.0652

Max Act: 5.9098. Min Act: -0.1700

Data Index: 1482949 (Open Web Text)

Max Activating Token Index: 506

Text #6

Max Range: 6.0652. Min Range: -6.0652

Max Act: 5.9012. Min Act: -0.1700

Data Index: 3253372 (Open Web Text)

Max Activating Token Index: 576

Text #7

Max Range: 6.0652. Min Range: -6.0652

Max Act: 5.8779. Min Act: -0.1700

Data Index: 5941738 (Open Web Text)

Max Activating Token Index: 667

Text #8

Max Range: 6.0652. Min Range: -6.0652

Max Act: 5.8634. Min Act: -0.1700

Data Index: 1862130 (Open Web Text)

Max Activating Token Index: 559

Text #9

Max Range: 6.0652. Min Range: -6.0652

Max Act: 5.8473. Min Act: -0.1700

Data Index: 5975607 (Open Web Text)

Max Activating Token Index: 590

Text #10

Max Range: 6.0652. Min Range: -6.0652

Max Act: 5.8260. Min Act: -0.1700

Data Index: 4863712 (Open Web Text)

Max Activating Token Index: 237

Text #11

Max Range: 6.0652. Min Range: -6.0652

Max Act: 5.8126. Min Act: -0.1700

Data Index: 2527963 (Open Web Text)

Max Activating Token Index: 818

Text #12

Max Range: 6.0652. Min Range: -6.0652

Max Act: 5.8239. Min Act: -0.1700

Data Index: 5335633 (Open Web Text)

Max Activating Token Index: 596

Text #13

Max Range: 6.0652. Min Range: -6.0652

Max Act: 5.8043. Min Act: -0.1700

Data Index: 4868943 (Open Web Text)

Max Activating Token Index: 146

Text #14

Max Range: 6.0652. Min Range: -6.0652

Max Act: 5.8020. Min Act: -0.1700

Data Index: 6512570 (Open Web Text)

Max Activating Token Index: 473

Text #15

Max Range: 6.0652. Min Range: -6.0652

Max Act: 5.7576. Min Act: -0.1700

Data Index: 381916 (Open Web Text)

Max Activating Token Index: 668

Text #16

Max Range: 6.0652. Min Range: -6.0652

Max Act: 5.7623. Min Act: -0.1700

Data Index: 3581615 (Open Web Text)

Max Activating Token Index: 158

Text #17

Max Range: 6.0652. Min Range: -6.0652

Max Act: 5.7624. Min Act: -0.1700

Data Index: 2831427 (Open Web Text)

Max Activating Token Index: 187

Text #18

Max Range: 6.0652. Min Range: -6.0652

Max Act: 5.7753. Min Act: -0.1700

Data Index: 2595271 (Open Web Text)

Max Activating Token Index: 131

Text #19

Max Range: 6.0652. Min Range: -6.0652

Max Act: 5.7694. Min Act: -0.1700

Data Index: 2375386 (Open Web Text)

Max Activating Token Index: 503