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

Dataset: Open Web Text

Neuron 2191 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: 3.6997. Min Range: -3.6997

Max Act: 3.6997. Min Act: -0.1700

Data Index: 5191796 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.6379. Min Act: -0.1700

Data Index: 5918369 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.6194. Min Act: -0.1700

Data Index: 2212965 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.6011. Min Act: -0.1700

Data Index: 4496803 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.6164. Min Act: -0.1700

Data Index: 8696110 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.6086. Min Act: -0.1700

Data Index: 2371653 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5655. Min Act: -0.1700

Data Index: 7035540 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5640. Min Act: -0.1700

Data Index: 6587805 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5656. Min Act: -0.1700

Data Index: 548070 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5847. Min Act: -0.1700

Data Index: 4650403 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5711. Min Act: -0.1700

Data Index: 4906512 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5656. Min Act: -0.1700

Data Index: 5262624 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5656. Min Act: -0.1700

Data Index: 1241656 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5656. Min Act: -0.1700

Data Index: 3975999 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5656. Min Act: -0.1700

Data Index: 6133325 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5369. Min Act: -0.1700

Data Index: 7629817 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5285. Min Act: -0.1700

Data Index: 2389095 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5324. Min Act: -0.1700

Data Index: 8175585 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5479. Min Act: -0.1700

Data Index: 500623 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.6997. Min Range: -3.6997

Max Act: 3.5582. Min Act: -0.1700

Data Index: 8480413 (Open Web Text)

Max Activating Token Index: 3