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

Dataset: Open Web Text

Neuron 21 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: 3.8920. Min Range: -3.8920

Max Act: 3.8920. Min Act: -0.1700

Data Index: 6937364 (Open Web Text)

Max Activating Token Index: 148

Text #1

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.7633. Min Act: -0.1700

Data Index: 2608178 (Open Web Text)

Max Activating Token Index: 445

Text #2

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.7430. Min Act: -0.1700

Data Index: 3876444 (Open Web Text)

Max Activating Token Index: 363

Text #3

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.7281. Min Act: -0.1700

Data Index: 4897793 (Open Web Text)

Max Activating Token Index: 269

Text #4

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.7321. Min Act: -0.1700

Data Index: 4445459 (Open Web Text)

Max Activating Token Index: 921

Text #5

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.6994. Min Act: -0.1700

Data Index: 2473656 (Open Web Text)

Max Activating Token Index: 83

Text #6

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.7107. Min Act: -0.1700

Data Index: 5420130 (Open Web Text)

Max Activating Token Index: 606

Text #7

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.6981. Min Act: -0.1700

Data Index: 98460 (Open Web Text)

Max Activating Token Index: 911

Text #8

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.6773. Min Act: -0.1700

Data Index: 5303364 (Open Web Text)

Max Activating Token Index: 763

Text #9

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.7004. Min Act: -0.1700

Data Index: 1523828 (Open Web Text)

Max Activating Token Index: 573

Text #10

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.7066. Min Act: -0.1700

Data Index: 217258 (Open Web Text)

Max Activating Token Index: 535

Text #11

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.6943. Min Act: -0.1700

Data Index: 3130882 (Open Web Text)

Max Activating Token Index: 588

Text #12

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.7006. Min Act: -0.1700

Data Index: 5390757 (Open Web Text)

Max Activating Token Index: 915

Text #13

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.6757. Min Act: -0.1700

Data Index: 5776567 (Open Web Text)

Max Activating Token Index: 615

Text #14

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.6771. Min Act: -0.1700

Data Index: 1692765 (Open Web Text)

Max Activating Token Index: 820

Text #15

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.6479. Min Act: -0.1700

Data Index: 4395193 (Open Web Text)

Max Activating Token Index: 729

Text #16

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.6636. Min Act: -0.1700

Data Index: 8344474 (Open Web Text)

Max Activating Token Index: 603

Text #17

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.6526. Min Act: -0.1700

Data Index: 4724551 (Open Web Text)

Max Activating Token Index: 230

Text #18

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.6533. Min Act: -0.1700

Data Index: 4104822 (Open Web Text)

Max Activating Token Index: 992

Text #19

Max Range: 3.8920. Min Range: -3.8920

Max Act: 3.6444. Min Act: -0.1700

Data Index: 306233 (Open Web Text)

Max Activating Token Index: 552