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

Dataset: Open Web Text

Neuron 2522 in Layer 6

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: 4.1066. Min Range: -4.1066

Max Act: 4.0739. Min Act: -0.1700

Data Index: 3780022 (Open Web Text)

Max Activating Token Index: 90

Text #1

Max Range: 4.1066. Min Range: -4.1066

Max Act: 4.0518. Min Act: -0.1700

Data Index: 544759 (Open Web Text)

Max Activating Token Index: 789

Text #2

Max Range: 4.1066. Min Range: -4.1066

Max Act: 4.1066. Min Act: -0.1700

Data Index: 8050808 (Open Web Text)

Max Activating Token Index: 816

Text #3

Max Range: 4.1066. Min Range: -4.1066

Max Act: 4.0005. Min Act: -0.1700

Data Index: 4481302 (Open Web Text)

Max Activating Token Index: 513

Text #4

Max Range: 4.1066. Min Range: -4.1066

Max Act: 3.9980. Min Act: -0.1700

Data Index: 3045271 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 4.1066. Min Range: -4.1066

Max Act: 3.9884. Min Act: -0.1700

Data Index: 4471944 (Open Web Text)

Max Activating Token Index: 814

Text #6

Max Range: 4.1066. Min Range: -4.1066

Max Act: 3.9964. Min Act: -0.1700

Data Index: 485596 (Open Web Text)

Max Activating Token Index: 414

Text #7

Max Range: 4.1066. Min Range: -4.1066

Max Act: 3.9552. Min Act: -0.1700

Data Index: 1027585 (Open Web Text)

Max Activating Token Index: 66

Text #8

Max Range: 4.1066. Min Range: -4.1066

Max Act: 3.9494. Min Act: -0.1700

Data Index: 5612420 (Open Web Text)

Max Activating Token Index: 643

Text #9

Max Range: 4.1066. Min Range: -4.1066

Max Act: 3.9575. Min Act: -0.1700

Data Index: 5375268 (Open Web Text)

Max Activating Token Index: 627

Text #10

Max Range: 4.1066. Min Range: -4.1066

Max Act: 3.9506. Min Act: -0.1700

Data Index: 5357738 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 4.1066. Min Range: -4.1066

Max Act: 3.9622. Min Act: -0.1700

Data Index: 31329 (Open Web Text)

Max Activating Token Index: 990

Text #12

Max Range: 4.1066. Min Range: -4.1066

Max Act: 3.9287. Min Act: -0.1700

Data Index: 2647616 (Open Web Text)

Max Activating Token Index: 534

Text #13

Max Range: 4.1066. Min Range: -4.1066

Max Act: 3.8861. Min Act: -0.1700

Data Index: 4135163 (Open Web Text)

Max Activating Token Index: 898

Text #14

Max Range: 4.1066. Min Range: -4.1066

Max Act: 3.9145. Min Act: -0.1700

Data Index: 6961030 (Open Web Text)

Max Activating Token Index: 311

Text #15

Max Range: 4.1066. Min Range: -4.1066

Max Act: 3.9315. Min Act: -0.1700

Data Index: 4249461 (Open Web Text)

Max Activating Token Index: 62

Text #16

Max Range: 4.1066. Min Range: -4.1066

Max Act: 3.9364. Min Act: -0.1700

Data Index: 8227285 (Open Web Text)

Max Activating Token Index: 673

Text #17

Max Range: 4.1066. Min Range: -4.1066

Max Act: 3.9012. Min Act: -0.1700

Data Index: 4421459 (Open Web Text)

Max Activating Token Index: 404

Text #18

Max Range: 4.1066. Min Range: -4.1066

Max Act: 3.9433. Min Act: -0.1700

Data Index: 4889552 (Open Web Text)

Max Activating Token Index: 868

Text #19

Max Range: 4.1066. Min Range: -4.1066

Max Act: 3.9351. Min Act: -0.1700

Data Index: 942851 (Open Web Text)

Max Activating Token Index: 525