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

Dataset: Open Web Text

Neuron 2441 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: 4.2944. Min Range: -4.2944

Max Act: 4.2944. Min Act: -0.1700

Data Index: 8802263 (Open Web Text)

Max Activating Token Index: 577

Text #1

Max Range: 4.2944. Min Range: -4.2944

Max Act: 3.9817. Min Act: -0.1700

Data Index: 4836736 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 4.2944. Min Range: -4.2944

Max Act: 3.9397. Min Act: -0.1700

Data Index: 4396530 (Open Web Text)

Max Activating Token Index: 628

Text #3

Max Range: 4.2944. Min Range: -4.2944

Max Act: 3.8741. Min Act: -0.1700

Data Index: 1795736 (Open Web Text)

Max Activating Token Index: 660

Text #4

Max Range: 4.2944. Min Range: -4.2944

Max Act: 3.8460. Min Act: -0.1700

Data Index: 1000236 (Open Web Text)

Max Activating Token Index: 965

Text #5

Max Range: 4.2944. Min Range: -4.2944

Max Act: 3.8647. Min Act: -0.1700

Data Index: 989216 (Open Web Text)

Max Activating Token Index: 854

Text #6

Max Range: 4.2944. Min Range: -4.2944

Max Act: 3.8507. Min Act: -0.1700

Data Index: 5323268 (Open Web Text)

Max Activating Token Index: 812

Text #7

Max Range: 4.2944. Min Range: -4.2944

Max Act: 3.8524. Min Act: -0.1700

Data Index: 8479645 (Open Web Text)

Max Activating Token Index: 38

Text #8

Max Range: 4.2944. Min Range: -4.2944

Max Act: 3.8295. Min Act: -0.1700

Data Index: 1100663 (Open Web Text)

Max Activating Token Index: 332

Text #9

Max Range: 4.2944. Min Range: -4.2944

Max Act: 3.8505. Min Act: -0.1700

Data Index: 3057936 (Open Web Text)

Max Activating Token Index: 809

Text #10

Max Range: 4.2944. Min Range: -4.2944

Max Act: 3.7862. Min Act: -0.1700

Data Index: 4017272 (Open Web Text)

Max Activating Token Index: 249

Text #11

Max Range: 4.2944. Min Range: -4.2944

Max Act: 3.7881. Min Act: -0.1700

Data Index: 908719 (Open Web Text)

Max Activating Token Index: 619

Text #12

Max Range: 4.2944. Min Range: -4.2944

Max Act: 3.7637. Min Act: -0.1700

Data Index: 8611371 (Open Web Text)

Max Activating Token Index: 883

Text #13

Max Range: 4.2944. Min Range: -4.2944

Max Act: 3.7777. Min Act: -0.1700

Data Index: 8028633 (Open Web Text)

Max Activating Token Index: 887

Text #14

Max Range: 4.2944. Min Range: -4.2944

Max Act: 3.7693. Min Act: -0.1700

Data Index: 2603832 (Open Web Text)

Max Activating Token Index: 959

Text #15

Max Range: 4.2944. Min Range: -4.2944

Max Act: 3.7895. Min Act: -0.1700

Data Index: 4017273 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 4.2944. Min Range: -4.2944

Max Act: 3.7214. Min Act: -0.1700

Data Index: 4879838 (Open Web Text)

Max Activating Token Index: 194

Text #17

Max Range: 4.2944. Min Range: -4.2944

Max Act: 3.7471. Min Act: -0.1700

Data Index: 2914515 (Open Web Text)

Max Activating Token Index: 625

Text #18

Max Range: 4.2944. Min Range: -4.2944

Max Act: 3.7230. Min Act: -0.1700

Data Index: 7977085 (Open Web Text)

Max Activating Token Index: 387

Text #19

Max Range: 4.2944. Min Range: -4.2944

Max Act: 3.7598. Min Act: -0.1700

Data Index: 7821009 (Open Web Text)

Max Activating Token Index: 37