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

Dataset: Open Web Text

Neuron 752 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: 5.0124. Min Range: -5.0124

Max Act: 4.9942. Min Act: -0.1700

Data Index: 986424 (Open Web Text)

Max Activating Token Index: 686

Text #1

Max Range: 5.0124. Min Range: -5.0124

Max Act: 4.9900. Min Act: -0.1700

Data Index: 6969376 (Open Web Text)

Max Activating Token Index: 491

Text #2

Max Range: 5.0124. Min Range: -5.0124

Max Act: 5.0036. Min Act: -0.1700

Data Index: 3532219 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 5.0124. Min Range: -5.0124

Max Act: 5.0034. Min Act: -0.1700

Data Index: 6992149 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 5.0124. Min Range: -5.0124

Max Act: 5.0124. Min Act: -0.1700

Data Index: 8629551 (Open Web Text)

Max Activating Token Index: 553

Text #5

Max Range: 5.0124. Min Range: -5.0124

Max Act: 4.9841. Min Act: -0.1700

Data Index: 1770831 (Open Web Text)

Max Activating Token Index: 16

Text #6

Max Range: 5.0124. Min Range: -5.0124

Max Act: 4.9868. Min Act: -0.1700

Data Index: 5757957 (Open Web Text)

Max Activating Token Index: 483

Text #7

Max Range: 5.0124. Min Range: -5.0124

Max Act: 4.9827. Min Act: -0.1700

Data Index: 3336962 (Open Web Text)

Max Activating Token Index: 722

Text #8

Max Range: 5.0124. Min Range: -5.0124

Max Act: 4.9714. Min Act: -0.1700

Data Index: 2700910 (Open Web Text)

Max Activating Token Index: 602

Text #9

Max Range: 5.0124. Min Range: -5.0124

Max Act: 4.9694. Min Act: -0.1700

Data Index: 2627326 (Open Web Text)

Max Activating Token Index: 478

Text #10

Max Range: 5.0124. Min Range: -5.0124

Max Act: 4.9839. Min Act: -0.1700

Data Index: 5605024 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 5.0124. Min Range: -5.0124

Max Act: 4.9379. Min Act: -0.1700

Data Index: 865714 (Open Web Text)

Max Activating Token Index: 365

Text #12

Max Range: 5.0124. Min Range: -5.0124

Max Act: 4.9407. Min Act: -0.1700

Data Index: 1709192 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 5.0124. Min Range: -5.0124

Max Act: 4.9387. Min Act: -0.1700

Data Index: 1386593 (Open Web Text)

Max Activating Token Index: 98

Text #14

Max Range: 5.0124. Min Range: -5.0124

Max Act: 4.9322. Min Act: -0.1700

Data Index: 3206843 (Open Web Text)

Max Activating Token Index: 559

Text #15

Max Range: 5.0124. Min Range: -5.0124

Max Act: 4.9542. Min Act: -0.1700

Data Index: 3308847 (Open Web Text)

Max Activating Token Index: 612

Text #16

Max Range: 5.0124. Min Range: -5.0124

Max Act: 4.9471. Min Act: -0.1700

Data Index: 2313189 (Open Web Text)

Max Activating Token Index: 654

Text #17

Max Range: 5.0124. Min Range: -5.0124

Max Act: 4.9451. Min Act: -0.1700

Data Index: 4263989 (Open Web Text)

Max Activating Token Index: 532

Text #18

Max Range: 5.0124. Min Range: -5.0124

Max Act: 4.9486. Min Act: -0.1700

Data Index: 2369135 (Open Web Text)

Max Activating Token Index: 610

Text #19

Max Range: 5.0124. Min Range: -5.0124

Max Act: 4.9610. Min Act: -0.1700

Data Index: 4328380 (Open Web Text)

Max Activating Token Index: 629