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

Dataset: Open Web Text

Neuron 1455 in Layer 5

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: 4.1089. Min Range: -4.1089

Max Act: 4.1089. Min Act: -0.1700

Data Index: 4855419 (Open Web Text)

Max Activating Token Index: 564

Text #1

Max Range: 4.1089. Min Range: -4.1089

Max Act: 3.9856. Min Act: -0.1700

Data Index: 1984193 (Open Web Text)

Max Activating Token Index: 610

Text #2

Max Range: 4.1089. Min Range: -4.1089

Max Act: 4.0474. Min Act: -0.1700

Data Index: 1984190 (Open Web Text)

Max Activating Token Index: 947

Text #3

Max Range: 4.1089. Min Range: -4.1089

Max Act: 4.0388. Min Act: -0.1700

Data Index: 5970993 (Open Web Text)

Max Activating Token Index: 461

Text #4

Max Range: 4.1089. Min Range: -4.1089

Max Act: 4.0904. Min Act: -0.1700

Data Index: 8356205 (Open Web Text)

Max Activating Token Index: 606

Text #5

Max Range: 4.1089. Min Range: -4.1089

Max Act: 3.9782. Min Act: -0.1700

Data Index: 7895160 (Open Web Text)

Max Activating Token Index: 126

Text #6

Max Range: 4.1089. Min Range: -4.1089

Max Act: 3.9579. Min Act: -0.1700

Data Index: 7316460 (Open Web Text)

Max Activating Token Index: 947

Text #7

Max Range: 4.1089. Min Range: -4.1089

Max Act: 3.9437. Min Act: -0.1700

Data Index: 7308631 (Open Web Text)

Max Activating Token Index: 589

Text #8

Max Range: 4.1089. Min Range: -4.1089

Max Act: 3.9270. Min Act: -0.1700

Data Index: 6071669 (Open Web Text)

Max Activating Token Index: 392

Text #9

Max Range: 4.1089. Min Range: -4.1089

Max Act: 3.9225. Min Act: -0.1700

Data Index: 667780 (Open Web Text)

Max Activating Token Index: 101

Text #10

Max Range: 4.1089. Min Range: -4.1089

Max Act: 3.9150. Min Act: -0.1700

Data Index: 5910931 (Open Web Text)

Max Activating Token Index: 259

Text #11

Max Range: 4.1089. Min Range: -4.1089

Max Act: 3.9459. Min Act: -0.1700

Data Index: 7278344 (Open Web Text)

Max Activating Token Index: 601

Text #12

Max Range: 4.1089. Min Range: -4.1089

Max Act: 3.9059. Min Act: -0.1700

Data Index: 4266274 (Open Web Text)

Max Activating Token Index: 95

Text #13

Max Range: 4.1089. Min Range: -4.1089

Max Act: 3.9322. Min Act: -0.1700

Data Index: 3442578 (Open Web Text)

Max Activating Token Index: 398

Text #14

Max Range: 4.1089. Min Range: -4.1089

Max Act: 3.8988. Min Act: -0.1700

Data Index: 5991322 (Open Web Text)

Max Activating Token Index: 657

Text #15

Max Range: 4.1089. Min Range: -4.1089

Max Act: 3.9169. Min Act: -0.1700

Data Index: 608688 (Open Web Text)

Max Activating Token Index: 825

Text #16

Max Range: 4.1089. Min Range: -4.1089

Max Act: 3.8876. Min Act: -0.1700

Data Index: 135154 (Open Web Text)

Max Activating Token Index: 441

Text #17

Max Range: 4.1089. Min Range: -4.1089

Max Act: 3.8865. Min Act: -0.1700

Data Index: 6134104 (Open Web Text)

Max Activating Token Index: 466

Text #18

Max Range: 4.1089. Min Range: -4.1089

Max Act: 3.8828. Min Act: -0.1700

Data Index: 2118055 (Open Web Text)

Max Activating Token Index: 1020

Text #19

Max Range: 4.1089. Min Range: -4.1089

Max Act: 3.9158. Min Act: -0.1700

Data Index: 4743374 (Open Web Text)

Max Activating Token Index: 752