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

Dataset: Open Web Text

Neuron 2623 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: 4.6125. Min Range: -4.6125

Max Act: 4.6125. Min Act: -0.1700

Data Index: 4188452 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.6125. Min Range: -4.6125

Max Act: 4.5663. Min Act: -0.1700

Data Index: 212722 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.6125. Min Range: -4.6125

Max Act: 4.5222. Min Act: -0.1700

Data Index: 5742197 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 4.6125. Min Range: -4.6125

Max Act: 4.5050. Min Act: -0.1700

Data Index: 4500197 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.6125. Min Range: -4.6125

Max Act: 4.4564. Min Act: -0.1700

Data Index: 8627139 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.6125. Min Range: -4.6125

Max Act: 4.4159. Min Act: -0.1700

Data Index: 1880194 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.6125. Min Range: -4.6125

Max Act: 4.4232. Min Act: -0.1700

Data Index: 1091201 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.6125. Min Range: -4.6125

Max Act: 4.4088. Min Act: -0.1700

Data Index: 1905875 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.6125. Min Range: -4.6125

Max Act: 4.3879. Min Act: -0.1700

Data Index: 7637177 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 4.6125. Min Range: -4.6125

Max Act: 4.3213. Min Act: -0.1700

Data Index: 4198442 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 4.6125. Min Range: -4.6125

Max Act: 4.3427. Min Act: -0.1700

Data Index: 2394224 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 4.6125. Min Range: -4.6125

Max Act: 4.2996. Min Act: -0.1700

Data Index: 5345264 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 4.6125. Min Range: -4.6125

Max Act: 4.3110. Min Act: -0.1700

Data Index: 4312892 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 4.6125. Min Range: -4.6125

Max Act: 4.3041. Min Act: -0.1700

Data Index: 5041421 (Open Web Text)

Max Activating Token Index: 20

Text #14

Max Range: 4.6125. Min Range: -4.6125

Max Act: 4.2830. Min Act: -0.1700

Data Index: 6937655 (Open Web Text)

Max Activating Token Index: 117

Text #15

Max Range: 4.6125. Min Range: -4.6125

Max Act: 4.2644. Min Act: -0.1700

Data Index: 8067025 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 4.6125. Min Range: -4.6125

Max Act: 4.2648. Min Act: -0.1700

Data Index: 6733289 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 4.6125. Min Range: -4.6125

Max Act: 4.2884. Min Act: -0.1700

Data Index: 6860162 (Open Web Text)

Max Activating Token Index: 21

Text #18

Max Range: 4.6125. Min Range: -4.6125

Max Act: 4.2740. Min Act: -0.1700

Data Index: 4812487 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.6125. Min Range: -4.6125

Max Act: 4.2783. Min Act: -0.1700

Data Index: 2756445 (Open Web Text)

Max Activating Token Index: 4