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

Dataset: Open Web Text

Neuron 525 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: 2.4967. Min Range: -2.4967

Max Act: 2.4967. Min Act: -0.1700

Data Index: 8200495 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.4967. Min Range: -2.4967

Max Act: 2.4761. Min Act: -0.1700

Data Index: 3919313 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.4967. Min Range: -2.4967

Max Act: 2.4798. Min Act: -0.1700

Data Index: 1439852 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.4967. Min Range: -2.4967

Max Act: 2.4390. Min Act: -0.1700

Data Index: 7440588 (Open Web Text)

Max Activating Token Index: 31

Text #4

Max Range: 2.4967. Min Range: -2.4967

Max Act: 2.4320. Min Act: -0.1700

Data Index: 6957694 (Open Web Text)

Max Activating Token Index: 47

Text #5

Max Range: 2.4967. Min Range: -2.4967

Max Act: 2.4308. Min Act: -0.1700

Data Index: 1666493 (Open Web Text)

Max Activating Token Index: 31

Text #6

Max Range: 2.4967. Min Range: -2.4967

Max Act: 2.4156. Min Act: -0.1700

Data Index: 3987509 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.4967. Min Range: -2.4967

Max Act: 2.4236. Min Act: -0.1700

Data Index: 2435297 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 2.4967. Min Range: -2.4967

Max Act: 2.4062. Min Act: -0.1700

Data Index: 5757196 (Open Web Text)

Max Activating Token Index: 53

Text #9

Max Range: 2.4967. Min Range: -2.4967

Max Act: 2.3995. Min Act: -0.1700

Data Index: 5899897 (Open Web Text)

Max Activating Token Index: 20

Text #10

Max Range: 2.4967. Min Range: -2.4967

Max Act: 2.3976. Min Act: -0.1700

Data Index: 8184834 (Open Web Text)

Max Activating Token Index: 203

Text #11

Max Range: 2.4967. Min Range: -2.4967

Max Act: 2.3932. Min Act: -0.1700

Data Index: 2362533 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 2.4967. Min Range: -2.4967

Max Act: 2.4022. Min Act: -0.1700

Data Index: 887161 (Open Web Text)

Max Activating Token Index: 367

Text #13

Max Range: 2.4967. Min Range: -2.4967

Max Act: 2.3917. Min Act: -0.1700

Data Index: 1673970 (Open Web Text)

Max Activating Token Index: 69

Text #14

Max Range: 2.4967. Min Range: -2.4967

Max Act: 2.3852. Min Act: -0.1700

Data Index: 5922808 (Open Web Text)

Max Activating Token Index: 501

Text #15

Max Range: 2.4967. Min Range: -2.4967

Max Act: 2.3776. Min Act: -0.1700

Data Index: 1326241 (Open Web Text)

Max Activating Token Index: 37

Text #16

Max Range: 2.4967. Min Range: -2.4967

Max Act: 2.3952. Min Act: -0.1700

Data Index: 7540801 (Open Web Text)

Max Activating Token Index: 190

Text #17

Max Range: 2.4967. Min Range: -2.4967

Max Act: 2.3896. Min Act: -0.1700

Data Index: 7630688 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.4967. Min Range: -2.4967

Max Act: 2.3791. Min Act: -0.1700

Data Index: 3830 (Open Web Text)

Max Activating Token Index: 526

Text #19

Max Range: 2.4967. Min Range: -2.4967

Max Act: 2.3750. Min Act: -0.1700

Data Index: 8460905 (Open Web Text)

Max Activating Token Index: 645