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

Dataset: Open Web Text

Neuron 1786 in Layer 0

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: 3.8732. Min Range: -3.8732

Max Act: 3.8732. Min Act: -0.1700

Data Index: 2727808 (Open Web Text)

Max Activating Token Index: 726

Text #1

Max Range: 3.8732. Min Range: -3.8732

Max Act: 3.8579. Min Act: -0.1700

Data Index: 6892013 (Open Web Text)

Max Activating Token Index: 245

Text #2

Max Range: 3.8732. Min Range: -3.8732

Max Act: 3.8121. Min Act: -0.1700

Data Index: 2431956 (Open Web Text)

Max Activating Token Index: 484

Text #3

Max Range: 3.8732. Min Range: -3.8732

Max Act: 3.7845. Min Act: -0.1700

Data Index: 6891998 (Open Web Text)

Max Activating Token Index: 801

Text #4

Max Range: 3.8732. Min Range: -3.8732

Max Act: 3.8059. Min Act: -0.1700

Data Index: 1442457 (Open Web Text)

Max Activating Token Index: 815

Text #5

Max Range: 3.8732. Min Range: -3.8732

Max Act: 3.7544. Min Act: -0.1700

Data Index: 6891999 (Open Web Text)

Max Activating Token Index: 611

Text #6

Max Range: 3.8732. Min Range: -3.8732

Max Act: 3.7400. Min Act: -0.1700

Data Index: 6563974 (Open Web Text)

Max Activating Token Index: 890

Text #7

Max Range: 3.8732. Min Range: -3.8732

Max Act: 3.7631. Min Act: -0.1700

Data Index: 6892012 (Open Web Text)

Max Activating Token Index: 435

Text #8

Max Range: 3.8732. Min Range: -3.8732

Max Act: 3.7423. Min Act: -0.1700

Data Index: 1300113 (Open Web Text)

Max Activating Token Index: 769

Text #9

Max Range: 3.8732. Min Range: -3.8732

Max Act: 3.6901. Min Act: -0.1700

Data Index: 2561658 (Open Web Text)

Max Activating Token Index: 314

Text #10

Max Range: 3.8732. Min Range: -3.8732

Max Act: 3.6864. Min Act: -0.1700

Data Index: 3829620 (Open Web Text)

Max Activating Token Index: 717

Text #11

Max Range: 3.8732. Min Range: -3.8732

Max Act: 3.6881. Min Act: -0.1700

Data Index: 6918311 (Open Web Text)

Max Activating Token Index: 888

Text #12

Max Range: 3.8732. Min Range: -3.8732

Max Act: 3.6998. Min Act: -0.1700

Data Index: 5270806 (Open Web Text)

Max Activating Token Index: 917

Text #13

Max Range: 3.8732. Min Range: -3.8732

Max Act: 3.6780. Min Act: -0.1700

Data Index: 8206378 (Open Web Text)

Max Activating Token Index: 1017

Text #14

Max Range: 3.8732. Min Range: -3.8732

Max Act: 3.6535. Min Act: -0.1700

Data Index: 2141493 (Open Web Text)

Max Activating Token Index: 289

Text #15

Max Range: 3.8732. Min Range: -3.8732

Max Act: 3.6785. Min Act: -0.1700

Data Index: 2561654 (Open Web Text)

Max Activating Token Index: 360

Text #16

Max Range: 3.8732. Min Range: -3.8732

Max Act: 3.6596. Min Act: -0.1700

Data Index: 7383068 (Open Web Text)

Max Activating Token Index: 868

Text #17

Max Range: 3.8732. Min Range: -3.8732

Max Act: 3.6332. Min Act: -0.1700

Data Index: 6179527 (Open Web Text)

Max Activating Token Index: 152

Text #18

Max Range: 3.8732. Min Range: -3.8732

Max Act: 3.6241. Min Act: -0.1700

Data Index: 2270262 (Open Web Text)

Max Activating Token Index: 562

Text #19

Max Range: 3.8732. Min Range: -3.8732

Max Act: 3.6491. Min Act: -0.1700

Data Index: 2561659 (Open Web Text)

Max Activating Token Index: 862