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

Dataset: Open Web Text

Neuron 2699 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: 3.8254. Min Range: -3.8254

Max Act: 3.8254. Min Act: -0.1700

Data Index: 1599457 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.7050. Min Act: -0.1700

Data Index: 5757538 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6464. Min Act: -0.1700

Data Index: 3446262 (Open Web Text)

Max Activating Token Index: 20

Text #3

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6494. Min Act: -0.1700

Data Index: 7474480 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5702. Min Act: -0.1700

Data Index: 4146843 (Open Web Text)

Max Activating Token Index: 22

Text #5

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5806. Min Act: -0.1700

Data Index: 1124241 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6031. Min Act: -0.1700

Data Index: 1973548 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6031. Min Act: -0.1700

Data Index: 5679313 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6079. Min Act: -0.1700

Data Index: 1361397 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6031. Min Act: -0.1700

Data Index: 37801 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.6079. Min Act: -0.1700

Data Index: 94006 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5747. Min Act: -0.1700

Data Index: 2571256 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5446. Min Act: -0.1700

Data Index: 7959930 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5420. Min Act: -0.1700

Data Index: 5512013 (Open Web Text)

Max Activating Token Index: 811

Text #14

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5718. Min Act: -0.1700

Data Index: 7504660 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5177. Min Act: -0.1700

Data Index: 2626962 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5126. Min Act: -0.1700

Data Index: 7018875 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5048. Min Act: -0.1700

Data Index: 44255 (Open Web Text)

Max Activating Token Index: 39

Text #18

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5443. Min Act: -0.1700

Data Index: 633637 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 3.8254. Min Range: -3.8254

Max Act: 3.5128. Min Act: -0.1700

Data Index: 3356185 (Open Web Text)

Max Activating Token Index: 40