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

Dataset: Open Web Text

Neuron 2618 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: 2.5749. Min Range: -2.5749

Max Act: 2.5749. Min Act: -0.1700

Data Index: 4060641 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.5749. Min Range: -2.5749

Max Act: 2.4463. Min Act: -0.1700

Data Index: 2946156 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.5749. Min Range: -2.5749

Max Act: 2.3935. Min Act: -0.1700

Data Index: 6544662 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 2.5749. Min Range: -2.5749

Max Act: 2.3785. Min Act: -0.1700

Data Index: 2333560 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.5749. Min Range: -2.5749

Max Act: 2.3724. Min Act: -0.1700

Data Index: 7333354 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.5749. Min Range: -2.5749

Max Act: 2.3180. Min Act: -0.1700

Data Index: 230778 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.5749. Min Range: -2.5749

Max Act: 2.3004. Min Act: -0.1700

Data Index: 4133851 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.5749. Min Range: -2.5749

Max Act: 2.3174. Min Act: -0.1700

Data Index: 1873355 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.5749. Min Range: -2.5749

Max Act: 2.3071. Min Act: -0.1700

Data Index: 6670658 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.5749. Min Range: -2.5749

Max Act: 2.2963. Min Act: -0.1700

Data Index: 6271651 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.5749. Min Range: -2.5749

Max Act: 2.2963. Min Act: -0.1700

Data Index: 8190936 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.5749. Min Range: -2.5749

Max Act: 2.2800. Min Act: -0.1700

Data Index: 7658199 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.5749. Min Range: -2.5749

Max Act: 2.2963. Min Act: -0.1700

Data Index: 7543540 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.5749. Min Range: -2.5749

Max Act: 2.2963. Min Act: -0.1700

Data Index: 1255086 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.5749. Min Range: -2.5749

Max Act: 2.2963. Min Act: -0.1700

Data Index: 6284719 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.5749. Min Range: -2.5749

Max Act: 2.2888. Min Act: -0.1700

Data Index: 1030941 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.5749. Min Range: -2.5749

Max Act: 2.2888. Min Act: -0.1700

Data Index: 1896495 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.5749. Min Range: -2.5749

Max Act: 2.2888. Min Act: -0.1700

Data Index: 2142695 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.5749. Min Range: -2.5749

Max Act: 2.2888. Min Act: -0.1700

Data Index: 974911 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.5749. Min Range: -2.5749

Max Act: 2.2888. Min Act: -0.1700

Data Index: 2068362 (Open Web Text)

Max Activating Token Index: 2