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

Dataset: Open Web Text

Neuron 2611 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: 4.8194. Min Range: -4.8194

Max Act: 4.8194. Min Act: -0.1700

Data Index: 2249154 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 4.8194. Min Range: -4.8194

Max Act: 4.7792. Min Act: -0.1700

Data Index: 4893191 (Open Web Text)

Max Activating Token Index: 779

Text #2

Max Range: 4.8194. Min Range: -4.8194

Max Act: 4.7099. Min Act: -0.1700

Data Index: 1593473 (Open Web Text)

Max Activating Token Index: 933

Text #3

Max Range: 4.8194. Min Range: -4.8194

Max Act: 4.7432. Min Act: -0.1700

Data Index: 5985452 (Open Web Text)

Max Activating Token Index: 667

Text #4

Max Range: 4.8194. Min Range: -4.8194

Max Act: 4.7154. Min Act: -0.1700

Data Index: 4563825 (Open Web Text)

Max Activating Token Index: 922

Text #5

Max Range: 4.8194. Min Range: -4.8194

Max Act: 4.7422. Min Act: -0.1700

Data Index: 8388564 (Open Web Text)

Max Activating Token Index: 775

Text #6

Max Range: 4.8194. Min Range: -4.8194

Max Act: 4.6828. Min Act: -0.1700

Data Index: 3060305 (Open Web Text)

Max Activating Token Index: 739

Text #7

Max Range: 4.8194. Min Range: -4.8194

Max Act: 4.6877. Min Act: -0.1700

Data Index: 6182700 (Open Web Text)

Max Activating Token Index: 820

Text #8

Max Range: 4.8194. Min Range: -4.8194

Max Act: 4.7014. Min Act: -0.1700

Data Index: 7471830 (Open Web Text)

Max Activating Token Index: 533

Text #9

Max Range: 4.8194. Min Range: -4.8194

Max Act: 4.6762. Min Act: -0.1700

Data Index: 4829880 (Open Web Text)

Max Activating Token Index: 772

Text #10

Max Range: 4.8194. Min Range: -4.8194

Max Act: 4.6777. Min Act: -0.1700

Data Index: 3508496 (Open Web Text)

Max Activating Token Index: 979

Text #11

Max Range: 4.8194. Min Range: -4.8194

Max Act: 4.6459. Min Act: -0.1700

Data Index: 8269120 (Open Web Text)

Max Activating Token Index: 682

Text #12

Max Range: 4.8194. Min Range: -4.8194

Max Act: 4.6597. Min Act: -0.1700

Data Index: 4707184 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.8194. Min Range: -4.8194

Max Act: 4.6620. Min Act: -0.1700

Data Index: 8289487 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.8194. Min Range: -4.8194

Max Act: 4.6631. Min Act: -0.1700

Data Index: 2966000 (Open Web Text)

Max Activating Token Index: 727

Text #15

Max Range: 4.8194. Min Range: -4.8194

Max Act: 4.6570. Min Act: -0.1700

Data Index: 7552448 (Open Web Text)

Max Activating Token Index: 957

Text #16

Max Range: 4.8194. Min Range: -4.8194

Max Act: 4.6737. Min Act: -0.1700

Data Index: 2038217 (Open Web Text)

Max Activating Token Index: 667

Text #17

Max Range: 4.8194. Min Range: -4.8194

Max Act: 4.6518. Min Act: -0.1700

Data Index: 3342247 (Open Web Text)

Max Activating Token Index: 766

Text #18

Max Range: 4.8194. Min Range: -4.8194

Max Act: 4.6506. Min Act: -0.1700

Data Index: 2195152 (Open Web Text)

Max Activating Token Index: 842

Text #19

Max Range: 4.8194. Min Range: -4.8194

Max Act: 4.6330. Min Act: -0.1700

Data Index: 2275053 (Open Web Text)

Max Activating Token Index: 1000