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

Dataset: Open Web Text

Neuron 2314 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: 3.0039. Min Range: -3.0039

Max Act: 2.9896. Min Act: -0.1700

Data Index: 1168307 (Open Web Text)

Max Activating Token Index: 559

Text #1

Max Range: 3.0039. Min Range: -3.0039

Max Act: 3.0039. Min Act: -0.1700

Data Index: 8227846 (Open Web Text)

Max Activating Token Index: 558

Text #2

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9903. Min Act: -0.1700

Data Index: 3808365 (Open Web Text)

Max Activating Token Index: 777

Text #3

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9793. Min Act: -0.1700

Data Index: 8146819 (Open Web Text)

Max Activating Token Index: 169

Text #4

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9716. Min Act: -0.1700

Data Index: 7663818 (Open Web Text)

Max Activating Token Index: 664

Text #5

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9362. Min Act: -0.1700

Data Index: 6922073 (Open Web Text)

Max Activating Token Index: 46

Text #6

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9335. Min Act: -0.1700

Data Index: 8537885 (Open Web Text)

Max Activating Token Index: 588

Text #7

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9569. Min Act: -0.1700

Data Index: 7050181 (Open Web Text)

Max Activating Token Index: 564

Text #8

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9277. Min Act: -0.1700

Data Index: 3319958 (Open Web Text)

Max Activating Token Index: 702

Text #9

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9185. Min Act: -0.1700

Data Index: 7796972 (Open Web Text)

Max Activating Token Index: 191

Text #10

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9263. Min Act: -0.1700

Data Index: 3329466 (Open Web Text)

Max Activating Token Index: 632

Text #11

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9155. Min Act: -0.1700

Data Index: 1055199 (Open Web Text)

Max Activating Token Index: 585

Text #12

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9362. Min Act: -0.1700

Data Index: 7008052 (Open Web Text)

Max Activating Token Index: 788

Text #13

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9303. Min Act: -0.1700

Data Index: 55401 (Open Web Text)

Max Activating Token Index: 641

Text #14

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9091. Min Act: -0.1700

Data Index: 1883799 (Open Web Text)

Max Activating Token Index: 158

Text #15

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9051. Min Act: -0.1700

Data Index: 143366 (Open Web Text)

Max Activating Token Index: 887

Text #16

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9059. Min Act: -0.1700

Data Index: 6522362 (Open Web Text)

Max Activating Token Index: 92

Text #17

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.9073. Min Act: -0.1700

Data Index: 1033234 (Open Web Text)

Max Activating Token Index: 364

Text #18

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.8974. Min Act: -0.1700

Data Index: 1751052 (Open Web Text)

Max Activating Token Index: 131

Text #19

Max Range: 3.0039. Min Range: -3.0039

Max Act: 2.8885. Min Act: -0.1700

Data Index: 6837970 (Open Web Text)

Max Activating Token Index: 54