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

Dataset: Open Web Text

Neuron 2135 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: 3.3057. Min Range: -3.3057

Max Act: 3.3057. Min Act: -0.1700

Data Index: 2167209 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.3057. Min Range: -3.3057

Max Act: 3.2967. Min Act: -0.1700

Data Index: 962680 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.3057. Min Range: -3.3057

Max Act: 3.2967. Min Act: -0.1700

Data Index: 6177161 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.3057. Min Range: -3.3057

Max Act: 3.2638. Min Act: -0.1700

Data Index: 5018921 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.3057. Min Range: -3.3057

Max Act: 3.2526. Min Act: -0.1700

Data Index: 4165134 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.3057. Min Range: -3.3057

Max Act: 3.2151. Min Act: -0.1700

Data Index: 4963336 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.3057. Min Range: -3.3057

Max Act: 3.1947. Min Act: -0.1700

Data Index: 5681229 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.3057. Min Range: -3.3057

Max Act: 3.1947. Min Act: -0.1700

Data Index: 6360955 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.3057. Min Range: -3.3057

Max Act: 3.1947. Min Act: -0.1700

Data Index: 8700120 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.3057. Min Range: -3.3057

Max Act: 3.1727. Min Act: -0.1700

Data Index: 1020752 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.3057. Min Range: -3.3057

Max Act: 3.1722. Min Act: -0.1700

Data Index: 3403515 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.3057. Min Range: -3.3057

Max Act: 3.1431. Min Act: -0.1700

Data Index: 2159331 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.3057. Min Range: -3.3057

Max Act: 3.1269. Min Act: -0.1700

Data Index: 6493528 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.3057. Min Range: -3.3057

Max Act: 3.1352. Min Act: -0.1700

Data Index: 2571020 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.3057. Min Range: -3.3057

Max Act: 3.1374. Min Act: -0.1700

Data Index: 3711320 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.3057. Min Range: -3.3057

Max Act: 3.1259. Min Act: -0.1700

Data Index: 5983144 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.3057. Min Range: -3.3057

Max Act: 3.1216. Min Act: -0.1700

Data Index: 3644808 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.3057. Min Range: -3.3057

Max Act: 3.1040. Min Act: -0.1700

Data Index: 4550903 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.3057. Min Range: -3.3057

Max Act: 3.0969. Min Act: -0.1700

Data Index: 2401556 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.3057. Min Range: -3.3057

Max Act: 3.0914. Min Act: -0.1700

Data Index: 3319730 (Open Web Text)

Max Activating Token Index: 4