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

Dataset: Open Web Text

Neuron 286 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: 3.5821. Min Range: -3.5821

Max Act: 3.5821. Min Act: -0.1700

Data Index: 7459054 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.5449. Min Act: -0.1700

Data Index: 8795539 (Open Web Text)

Max Activating Token Index: 454

Text #2

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.5400. Min Act: -0.1700

Data Index: 3439942 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.5246. Min Act: -0.1700

Data Index: 3004115 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.5504. Min Act: -0.1700

Data Index: 144938 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.4923. Min Act: -0.1700

Data Index: 4245654 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.5063. Min Act: -0.1700

Data Index: 3811456 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.5168. Min Act: -0.1700

Data Index: 5220232 (Open Web Text)

Max Activating Token Index: 30

Text #8

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.4405. Min Act: -0.1700

Data Index: 2990104 (Open Web Text)

Max Activating Token Index: 18

Text #9

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.4428. Min Act: -0.1700

Data Index: 3621025 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.4469. Min Act: -0.1700

Data Index: 8527642 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.4341. Min Act: -0.1700

Data Index: 8547417 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.4636. Min Act: -0.1700

Data Index: 2121138 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.4443. Min Act: -0.1700

Data Index: 7659155 (Open Web Text)

Max Activating Token Index: 582

Text #14

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.4560. Min Act: -0.1700

Data Index: 2132180 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.4300. Min Act: -0.1700

Data Index: 649750 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.4117. Min Act: -0.1700

Data Index: 860309 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.4160. Min Act: -0.1700

Data Index: 6084210 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.4091. Min Act: -0.1700

Data Index: 6732428 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.4048. Min Act: -0.1700

Data Index: 3954885 (Open Web Text)

Max Activating Token Index: 15