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

Dataset: Open Web Text

Neuron 1285 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: 3.3371. Min Range: -3.3371

Max Act: 3.3371. Min Act: -0.1700

Data Index: 7939551 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.2990. Min Act: -0.1700

Data Index: 6140099 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.2909. Min Act: -0.1700

Data Index: 5918955 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.2943. Min Act: -0.1700

Data Index: 1727608 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.2915. Min Act: -0.1700

Data Index: 3042209 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.3052. Min Act: -0.1700

Data Index: 4053357 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.2996. Min Act: -0.1700

Data Index: 4585782 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.2585. Min Act: -0.1700

Data Index: 6410746 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.2364. Min Act: -0.1700

Data Index: 4824949 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.2285. Min Act: -0.1700

Data Index: 119838 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.2597. Min Act: -0.1700

Data Index: 1421644 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.2025. Min Act: -0.1700

Data Index: 6281662 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.1973. Min Act: -0.1700

Data Index: 4698699 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.1945. Min Act: -0.1700

Data Index: 782487 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.1860. Min Act: -0.1700

Data Index: 6757894 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.2139. Min Act: -0.1700

Data Index: 4979633 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.2223. Min Act: -0.1700

Data Index: 12816 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.1907. Min Act: -0.1700

Data Index: 718187 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.1817. Min Act: -0.1700

Data Index: 7949316 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.2039. Min Act: -0.1700

Data Index: 8255311 (Open Web Text)

Max Activating Token Index: 3