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

Dataset: Open Web Text

Neuron 749 in Layer 2

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: 1.8593. Min Range: -1.8593

Max Act: 1.8593. Min Act: -0.1700

Data Index: 3417318 (Open Web Text)

Max Activating Token Index: 965

Text #1

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.8403. Min Act: -0.1700

Data Index: 3950176 (Open Web Text)

Max Activating Token Index: 872

Text #2

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.8543. Min Act: -0.1700

Data Index: 6643556 (Open Web Text)

Max Activating Token Index: 308

Text #3

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.8169. Min Act: -0.1700

Data Index: 850030 (Open Web Text)

Max Activating Token Index: 927

Text #4

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.8177. Min Act: -0.1700

Data Index: 4883496 (Open Web Text)

Max Activating Token Index: 384

Text #5

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.8204. Min Act: -0.1700

Data Index: 5645719 (Open Web Text)

Max Activating Token Index: 757

Text #6

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.8200. Min Act: -0.1700

Data Index: 3901219 (Open Web Text)

Max Activating Token Index: 394

Text #7

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.8091. Min Act: -0.1700

Data Index: 910199 (Open Web Text)

Max Activating Token Index: 863

Text #8

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.8138. Min Act: -0.1700

Data Index: 6273190 (Open Web Text)

Max Activating Token Index: 502

Text #9

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.7986. Min Act: -0.1700

Data Index: 6493754 (Open Web Text)

Max Activating Token Index: 937

Text #10

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.7962. Min Act: -0.1700

Data Index: 7074293 (Open Web Text)

Max Activating Token Index: 79

Text #11

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.8002. Min Act: -0.1700

Data Index: 7921409 (Open Web Text)

Max Activating Token Index: 796

Text #12

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.8047. Min Act: -0.1700

Data Index: 5075278 (Open Web Text)

Max Activating Token Index: 143

Text #13

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.8169. Min Act: -0.1700

Data Index: 4795081 (Open Web Text)

Max Activating Token Index: 870

Text #14

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.7985. Min Act: -0.1700

Data Index: 941995 (Open Web Text)

Max Activating Token Index: 844

Text #15

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.7854. Min Act: -0.1700

Data Index: 8075275 (Open Web Text)

Max Activating Token Index: 356

Text #16

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.7905. Min Act: -0.1700

Data Index: 6522417 (Open Web Text)

Max Activating Token Index: 159

Text #17

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.7823. Min Act: -0.1700

Data Index: 3481633 (Open Web Text)

Max Activating Token Index: 700

Text #18

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.7837. Min Act: -0.1700

Data Index: 1665049 (Open Web Text)

Max Activating Token Index: 923

Text #19

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.7834. Min Act: -0.1700

Data Index: 5471926 (Open Web Text)

Max Activating Token Index: 890