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

Dataset: Open Web Text

Neuron 2174 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: 4.3505. Min Range: -4.3505

Max Act: 4.3505. Min Act: -0.1700

Data Index: 5139937 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.3505. Min Range: -4.3505

Max Act: 4.2961. Min Act: -0.1700

Data Index: 2108946 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.3505. Min Range: -4.3505

Max Act: 4.3149. Min Act: -0.1700

Data Index: 2506171 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.3505. Min Range: -4.3505

Max Act: 4.2828. Min Act: -0.1700

Data Index: 6051416 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.3505. Min Range: -4.3505

Max Act: 4.2830. Min Act: -0.1700

Data Index: 6020058 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.3505. Min Range: -4.3505

Max Act: 4.2260. Min Act: -0.1700

Data Index: 186136 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.3505. Min Range: -4.3505

Max Act: 4.2125. Min Act: -0.1700

Data Index: 6451520 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.3505. Min Range: -4.3505

Max Act: 4.1923. Min Act: -0.1700

Data Index: 4538055 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.3505. Min Range: -4.3505

Max Act: 4.2004. Min Act: -0.1700

Data Index: 2114438 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.3505. Min Range: -4.3505

Max Act: 4.2004. Min Act: -0.1700

Data Index: 937394 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.3505. Min Range: -4.3505

Max Act: 4.2184. Min Act: -0.1700

Data Index: 8061137 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.3505. Min Range: -4.3505

Max Act: 4.2195. Min Act: -0.1700

Data Index: 8382476 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.3505. Min Range: -4.3505

Max Act: 4.1834. Min Act: -0.1700

Data Index: 5142623 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.3505. Min Range: -4.3505

Max Act: 4.1775. Min Act: -0.1700

Data Index: 5432240 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.3505. Min Range: -4.3505

Max Act: 4.1796. Min Act: -0.1700

Data Index: 2066178 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.3505. Min Range: -4.3505

Max Act: 4.1689. Min Act: -0.1700

Data Index: 1290651 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.3505. Min Range: -4.3505

Max Act: 4.1591. Min Act: -0.1700

Data Index: 5751985 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 4.3505. Min Range: -4.3505

Max Act: 4.1839. Min Act: -0.1700

Data Index: 1977583 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.3505. Min Range: -4.3505

Max Act: 4.1591. Min Act: -0.1700

Data Index: 4169666 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 4.3505. Min Range: -4.3505

Max Act: 4.1691. Min Act: -0.1700

Data Index: 2201302 (Open Web Text)

Max Activating Token Index: 4