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

Dataset: Open Web Text

Neuron 1116 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: 2.9114. Min Range: -2.9114

Max Act: 2.9114. Min Act: -0.1700

Data Index: 5428495 (Open Web Text)

Max Activating Token Index: 947

Text #1

Max Range: 2.9114. Min Range: -2.9114

Max Act: 2.8829. Min Act: -0.1700

Data Index: 5803090 (Open Web Text)

Max Activating Token Index: 55

Text #2

Max Range: 2.9114. Min Range: -2.9114

Max Act: 2.8509. Min Act: -0.1700

Data Index: 1541666 (Open Web Text)

Max Activating Token Index: 521

Text #3

Max Range: 2.9114. Min Range: -2.9114

Max Act: 2.7889. Min Act: -0.1700

Data Index: 7292450 (Open Web Text)

Max Activating Token Index: 101

Text #4

Max Range: 2.9114. Min Range: -2.9114

Max Act: 2.8075. Min Act: -0.1700

Data Index: 8211295 (Open Web Text)

Max Activating Token Index: 522

Text #5

Max Range: 2.9114. Min Range: -2.9114

Max Act: 2.7895. Min Act: -0.1700

Data Index: 851026 (Open Web Text)

Max Activating Token Index: 863

Text #6

Max Range: 2.9114. Min Range: -2.9114

Max Act: 2.8512. Min Act: -0.1700

Data Index: 4020691 (Open Web Text)

Max Activating Token Index: 613

Text #7

Max Range: 2.9114. Min Range: -2.9114

Max Act: 2.7505. Min Act: -0.1700

Data Index: 7803070 (Open Web Text)

Max Activating Token Index: 472

Text #8

Max Range: 2.9114. Min Range: -2.9114

Max Act: 2.7879. Min Act: -0.1700

Data Index: 5564592 (Open Web Text)

Max Activating Token Index: 491

Text #9

Max Range: 2.9114. Min Range: -2.9114

Max Act: 2.7473. Min Act: -0.1700

Data Index: 7151968 (Open Web Text)

Max Activating Token Index: 712

Text #10

Max Range: 2.9114. Min Range: -2.9114

Max Act: 2.7665. Min Act: -0.1700

Data Index: 7212574 (Open Web Text)

Max Activating Token Index: 253

Text #11

Max Range: 2.9114. Min Range: -2.9114

Max Act: 2.7462. Min Act: -0.1700

Data Index: 6793068 (Open Web Text)

Max Activating Token Index: 170

Text #12

Max Range: 2.9114. Min Range: -2.9114

Max Act: 2.7461. Min Act: -0.1700

Data Index: 7252641 (Open Web Text)

Max Activating Token Index: 907

Text #13

Max Range: 2.9114. Min Range: -2.9114

Max Act: 2.7565. Min Act: -0.1700

Data Index: 2753180 (Open Web Text)

Max Activating Token Index: 942

Text #14

Max Range: 2.9114. Min Range: -2.9114

Max Act: 2.7591. Min Act: -0.1700

Data Index: 8507684 (Open Web Text)

Max Activating Token Index: 429

Text #15

Max Range: 2.9114. Min Range: -2.9114

Max Act: 2.7491. Min Act: -0.1700

Data Index: 3428775 (Open Web Text)

Max Activating Token Index: 323

Text #16

Max Range: 2.9114. Min Range: -2.9114

Max Act: 2.7143. Min Act: -0.1700

Data Index: 461775 (Open Web Text)

Max Activating Token Index: 499

Text #17

Max Range: 2.9114. Min Range: -2.9114

Max Act: 2.7692. Min Act: -0.1700

Data Index: 8001799 (Open Web Text)

Max Activating Token Index: 951

Text #18

Max Range: 2.9114. Min Range: -2.9114

Max Act: 2.7475. Min Act: -0.1700

Data Index: 5050154 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.9114. Min Range: -2.9114

Max Act: 2.7308. Min Act: -0.1700

Data Index: 7500818 (Open Web Text)

Max Activating Token Index: 954