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

Dataset: Open Web Text

Neuron 1532 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: 3.1012. Min Range: -3.1012

Max Act: 3.1012. Min Act: -0.1700

Data Index: 1706240 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.1012. Min Range: -3.1012

Max Act: 3.0669. Min Act: -0.1700

Data Index: 5617291 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.1012. Min Range: -3.1012

Max Act: 3.0613. Min Act: -0.1700

Data Index: 4577748 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.1012. Min Range: -3.1012

Max Act: 3.0611. Min Act: -0.1700

Data Index: 5629079 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.1012. Min Range: -3.1012

Max Act: 3.0448. Min Act: -0.1700

Data Index: 2608160 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.1012. Min Range: -3.1012

Max Act: 3.0232. Min Act: -0.1700

Data Index: 6449355 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.1012. Min Range: -3.1012

Max Act: 3.0300. Min Act: -0.1700

Data Index: 4326535 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.1012. Min Range: -3.1012

Max Act: 3.0161. Min Act: -0.1700

Data Index: 6547810 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.9966. Min Act: -0.1700

Data Index: 7782036 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.9790. Min Act: -0.1700

Data Index: 1089890 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.9869. Min Act: -0.1700

Data Index: 2978452 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.9786. Min Act: -0.1700

Data Index: 5289871 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.9772. Min Act: -0.1700

Data Index: 502285 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.9657. Min Act: -0.1700

Data Index: 5530940 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.9652. Min Act: -0.1700

Data Index: 208885 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.9682. Min Act: -0.1700

Data Index: 8267110 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.9661. Min Act: -0.1700

Data Index: 2995400 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.9683. Min Act: -0.1700

Data Index: 7712560 (Open Web Text)

Max Activating Token Index: 953

Text #18

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.9603. Min Act: -0.1700

Data Index: 6132542 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.1012. Min Range: -3.1012

Max Act: 2.9400. Min Act: -0.1700

Data Index: 290524 (Open Web Text)

Max Activating Token Index: 2