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

Dataset: Open Web Text

Neuron 2189 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: 3.5877. Min Range: -3.5877

Max Act: 3.5877. Min Act: -0.1700

Data Index: 1731367 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.5877. Min Range: -3.5877

Max Act: 3.4727. Min Act: -0.1700

Data Index: 8786853 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 3.5877. Min Range: -3.5877

Max Act: 3.4824. Min Act: -0.1700

Data Index: 3949946 (Open Web Text)

Max Activating Token Index: 31

Text #3

Max Range: 3.5877. Min Range: -3.5877

Max Act: 3.4752. Min Act: -0.1700

Data Index: 3045733 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.5877. Min Range: -3.5877

Max Act: 3.4506. Min Act: -0.1700

Data Index: 4410197 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.5877. Min Range: -3.5877

Max Act: 3.4472. Min Act: -0.1700

Data Index: 397644 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 3.5877. Min Range: -3.5877

Max Act: 3.4357. Min Act: -0.1700

Data Index: 2007329 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.5877. Min Range: -3.5877

Max Act: 3.4050. Min Act: -0.1700

Data Index: 8337376 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.5877. Min Range: -3.5877

Max Act: 3.4249. Min Act: -0.1700

Data Index: 4013840 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 3.5877. Min Range: -3.5877

Max Act: 3.4131. Min Act: -0.1700

Data Index: 4349196 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 3.5877. Min Range: -3.5877

Max Act: 3.4055. Min Act: -0.1700

Data Index: 2040150 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 3.5877. Min Range: -3.5877

Max Act: 3.3915. Min Act: -0.1700

Data Index: 5561079 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.5877. Min Range: -3.5877

Max Act: 3.3778. Min Act: -0.1700

Data Index: 5297540 (Open Web Text)

Max Activating Token Index: 841

Text #13

Max Range: 3.5877. Min Range: -3.5877

Max Act: 3.3662. Min Act: -0.1700

Data Index: 2007833 (Open Web Text)

Max Activating Token Index: 890

Text #14

Max Range: 3.5877. Min Range: -3.5877

Max Act: 3.3747. Min Act: -0.1700

Data Index: 5081751 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 3.5877. Min Range: -3.5877

Max Act: 3.3817. Min Act: -0.1700

Data Index: 4542863 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.5877. Min Range: -3.5877

Max Act: 3.3799. Min Act: -0.1700

Data Index: 1846052 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.5877. Min Range: -3.5877

Max Act: 3.3950. Min Act: -0.1700

Data Index: 2669141 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 3.5877. Min Range: -3.5877

Max Act: 3.3934. Min Act: -0.1700

Data Index: 23897 (Open Web Text)

Max Activating Token Index: 49

Text #19

Max Range: 3.5877. Min Range: -3.5877

Max Act: 3.3870. Min Act: -0.1700

Data Index: 4330787 (Open Web Text)

Max Activating Token Index: 21