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

Dataset: Open Web Text

Neuron 2212 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: 4.9522. Min Range: -4.9522

Max Act: 4.9522. Min Act: -0.1700

Data Index: 5923634 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.9522. Min Range: -4.9522

Max Act: 4.9292. Min Act: -0.1700

Data Index: 2783950 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 4.9522. Min Range: -4.9522

Max Act: 4.8987. Min Act: -0.1700

Data Index: 1434203 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.9522. Min Range: -4.9522

Max Act: 4.8841. Min Act: -0.1700

Data Index: 959581 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.9522. Min Range: -4.9522

Max Act: 4.8413. Min Act: -0.1700

Data Index: 2204054 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.9522. Min Range: -4.9522

Max Act: 4.8453. Min Act: -0.1700

Data Index: 2876415 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.9522. Min Range: -4.9522

Max Act: 4.8209. Min Act: -0.1700

Data Index: 3679065 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.9522. Min Range: -4.9522

Max Act: 4.8315. Min Act: -0.1700

Data Index: 5832761 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.9522. Min Range: -4.9522

Max Act: 4.7831. Min Act: -0.1700

Data Index: 7401350 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.9522. Min Range: -4.9522

Max Act: 4.7742. Min Act: -0.1700

Data Index: 8385777 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.9522. Min Range: -4.9522

Max Act: 4.7973. Min Act: -0.1700

Data Index: 6760537 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.9522. Min Range: -4.9522

Max Act: 4.7875. Min Act: -0.1700

Data Index: 5158613 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.9522. Min Range: -4.9522

Max Act: 4.7890. Min Act: -0.1700

Data Index: 8703720 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 4.9522. Min Range: -4.9522

Max Act: 4.7928. Min Act: -0.1700

Data Index: 1719489 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.9522. Min Range: -4.9522

Max Act: 4.7501. Min Act: -0.1700

Data Index: 3345384 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.9522. Min Range: -4.9522

Max Act: 4.7559. Min Act: -0.1700

Data Index: 8740433 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.9522. Min Range: -4.9522

Max Act: 4.7447. Min Act: -0.1700

Data Index: 4041174 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.9522. Min Range: -4.9522

Max Act: 4.7492. Min Act: -0.1700

Data Index: 913944 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.9522. Min Range: -4.9522

Max Act: 4.7419. Min Act: -0.1700

Data Index: 3044911 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.9522. Min Range: -4.9522

Max Act: 4.7626. Min Act: -0.1700

Data Index: 1576575 (Open Web Text)

Max Activating Token Index: 7