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

Dataset: Open Web Text

Neuron 2642 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: 5.5605. Min Range: -5.5605

Max Act: 5.5408. Min Act: -0.1700

Data Index: 3174778 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.5605. Min Act: -0.1700

Data Index: 8446200 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.4944. Min Act: -0.1700

Data Index: 7358543 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.5016. Min Act: -0.1700

Data Index: 7213809 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.4803. Min Act: -0.1700

Data Index: 4661098 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.5053. Min Act: -0.1700

Data Index: 3825211 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.4793. Min Act: -0.1700

Data Index: 1058611 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.4500. Min Act: -0.1700

Data Index: 2097251 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.4405. Min Act: -0.1700

Data Index: 480965 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.4377. Min Act: -0.1700

Data Index: 6518814 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.4175. Min Act: -0.1700

Data Index: 580051 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.4186. Min Act: -0.1700

Data Index: 3140143 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.4156. Min Act: -0.1700

Data Index: 4607391 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.4156. Min Act: -0.1700

Data Index: 3723855 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.3814. Min Act: -0.1700

Data Index: 2705949 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.3735. Min Act: -0.1700

Data Index: 7044450 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.3832. Min Act: -0.1700

Data Index: 6234662 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.3693. Min Act: -0.1700

Data Index: 4266764 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.3935. Min Act: -0.1700

Data Index: 7219272 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 5.5605. Min Range: -5.5605

Max Act: 5.3957. Min Act: -0.1700

Data Index: 6080810 (Open Web Text)

Max Activating Token Index: 3