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

Dataset: Open Web Text

Neuron 472 in Layer 3

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: 4.4977. Min Range: -4.4977

Max Act: 4.4977. Min Act: -0.1700

Data Index: 3384863 (Open Web Text)

Max Activating Token Index: 195

Text #1

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.2456. Min Act: -0.1700

Data Index: 5390242 (Open Web Text)

Max Activating Token Index: 257

Text #2

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.2720. Min Act: -0.1700

Data Index: 1710901 (Open Web Text)

Max Activating Token Index: 544

Text #3

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.2425. Min Act: -0.1700

Data Index: 3384862 (Open Web Text)

Max Activating Token Index: 358

Text #4

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.2259. Min Act: -0.1700

Data Index: 5968581 (Open Web Text)

Max Activating Token Index: 124

Text #5

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.2369. Min Act: -0.1700

Data Index: 400904 (Open Web Text)

Max Activating Token Index: 75

Text #6

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.2027. Min Act: -0.1700

Data Index: 1561777 (Open Web Text)

Max Activating Token Index: 967

Text #7

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.1696. Min Act: -0.1700

Data Index: 2176480 (Open Web Text)

Max Activating Token Index: 199

Text #8

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.1289. Min Act: -0.1700

Data Index: 3944734 (Open Web Text)

Max Activating Token Index: 104

Text #9

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.0797. Min Act: -0.1700

Data Index: 3030426 (Open Web Text)

Max Activating Token Index: 204

Text #10

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.0944. Min Act: -0.1700

Data Index: 8691975 (Open Web Text)

Max Activating Token Index: 461

Text #11

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.0773. Min Act: -0.1700

Data Index: 880863 (Open Web Text)

Max Activating Token Index: 807

Text #12

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.0947. Min Act: -0.1700

Data Index: 8491785 (Open Web Text)

Max Activating Token Index: 364

Text #13

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.1193. Min Act: -0.1700

Data Index: 8361641 (Open Web Text)

Max Activating Token Index: 478

Text #14

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.0743. Min Act: -0.1700

Data Index: 6720652 (Open Web Text)

Max Activating Token Index: 377

Text #15

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.0991. Min Act: -0.1700

Data Index: 6526103 (Open Web Text)

Max Activating Token Index: 1003

Text #16

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.0654. Min Act: -0.1700

Data Index: 6439135 (Open Web Text)

Max Activating Token Index: 818

Text #17

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.1006. Min Act: -0.1700

Data Index: 6127226 (Open Web Text)

Max Activating Token Index: 551

Text #18

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.0863. Min Act: -0.1700

Data Index: 1542104 (Open Web Text)

Max Activating Token Index: 304

Text #19

Max Range: 4.4977. Min Range: -4.4977

Max Act: 4.0452. Min Act: -0.1700

Data Index: 2621204 (Open Web Text)

Max Activating Token Index: 947