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

Dataset: Open Web Text

Neuron 1983 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: 4.0632. Min Range: -4.0632

Max Act: 4.0632. Min Act: -0.1700

Data Index: 4587276 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.0632. Min Range: -4.0632

Max Act: 4.0340. Min Act: -0.1700

Data Index: 850840 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.0632. Min Range: -4.0632

Max Act: 3.9683. Min Act: -0.1700

Data Index: 924613 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.0632. Min Range: -4.0632

Max Act: 3.9264. Min Act: -0.1700

Data Index: 702320 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.0632. Min Range: -4.0632

Max Act: 3.9223. Min Act: -0.1700

Data Index: 3879984 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.0632. Min Range: -4.0632

Max Act: 3.9004. Min Act: -0.1700

Data Index: 1909675 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.0632. Min Range: -4.0632

Max Act: 3.9031. Min Act: -0.1700

Data Index: 94716 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.0632. Min Range: -4.0632

Max Act: 3.8929. Min Act: -0.1700

Data Index: 1398173 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.0632. Min Range: -4.0632

Max Act: 3.8835. Min Act: -0.1700

Data Index: 3835027 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.0632. Min Range: -4.0632

Max Act: 3.8813. Min Act: -0.1700

Data Index: 4319941 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.0632. Min Range: -4.0632

Max Act: 3.8918. Min Act: -0.1700

Data Index: 6532858 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.0632. Min Range: -4.0632

Max Act: 3.8841. Min Act: -0.1700

Data Index: 1414742 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.0632. Min Range: -4.0632

Max Act: 3.8883. Min Act: -0.1700

Data Index: 8817326 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.0632. Min Range: -4.0632

Max Act: 3.8821. Min Act: -0.1700

Data Index: 4456297 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.0632. Min Range: -4.0632

Max Act: 3.8814. Min Act: -0.1700

Data Index: 8549125 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 4.0632. Min Range: -4.0632

Max Act: 3.8739. Min Act: -0.1700

Data Index: 5526007 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.0632. Min Range: -4.0632

Max Act: 3.8905. Min Act: -0.1700

Data Index: 6991427 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.0632. Min Range: -4.0632

Max Act: 3.8742. Min Act: -0.1700

Data Index: 5692339 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.0632. Min Range: -4.0632

Max Act: 3.8531. Min Act: -0.1700

Data Index: 6868088 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.0632. Min Range: -4.0632

Max Act: 3.8664. Min Act: -0.1700

Data Index: 2136608 (Open Web Text)

Max Activating Token Index: 3