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

Dataset: Open Web Text

Neuron 3063 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: 2.9588. Min Range: -2.9588

Max Act: 2.9571. Min Act: -0.1700

Data Index: 4461259 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.9542. Min Act: -0.1700

Data Index: 4916411 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.9588. Min Act: -0.1700

Data Index: 8420936 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.9547. Min Act: -0.1700

Data Index: 1007346 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.9421. Min Act: -0.1700

Data Index: 4118775 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.9514. Min Act: -0.1700

Data Index: 3002453 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.9336. Min Act: -0.1700

Data Index: 4792946 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.9271. Min Act: -0.1700

Data Index: 5199607 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.9283. Min Act: -0.1700

Data Index: 5496964 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.9282. Min Act: -0.1700

Data Index: 1238911 (Open Web Text)

Max Activating Token Index: 18

Text #10

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.9336. Min Act: -0.1700

Data Index: 4411702 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.9229. Min Act: -0.1700

Data Index: 4246553 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.9098. Min Act: -0.1700

Data Index: 3118897 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.9057. Min Act: -0.1700

Data Index: 3481518 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.9181. Min Act: -0.1700

Data Index: 6761218 (Open Web Text)

Max Activating Token Index: 18

Text #15

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.9067. Min Act: -0.1700

Data Index: 1496086 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.8959. Min Act: -0.1700

Data Index: 4596957 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.8925. Min Act: -0.1700

Data Index: 3825058 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.8889. Min Act: -0.1700

Data Index: 638700 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.9028. Min Act: -0.1700

Data Index: 1445943 (Open Web Text)

Max Activating Token Index: 11