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

Dataset: Open Web Text

Neuron 1040 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: 3.2617. Min Range: -3.2617

Max Act: 3.2617. Min Act: -0.1700

Data Index: 4949593 (Open Web Text)

Max Activating Token Index: 526

Text #1

Max Range: 3.2617. Min Range: -3.2617

Max Act: 3.0270. Min Act: -0.1700

Data Index: 5617338 (Open Web Text)

Max Activating Token Index: 482

Text #2

Max Range: 3.2617. Min Range: -3.2617

Max Act: 2.9964. Min Act: -0.1700

Data Index: 203502 (Open Web Text)

Max Activating Token Index: 266

Text #3

Max Range: 3.2617. Min Range: -3.2617

Max Act: 2.9973. Min Act: -0.1700

Data Index: 3140772 (Open Web Text)

Max Activating Token Index: 610

Text #4

Max Range: 3.2617. Min Range: -3.2617

Max Act: 2.9957. Min Act: -0.1700

Data Index: 1444445 (Open Web Text)

Max Activating Token Index: 518

Text #5

Max Range: 3.2617. Min Range: -3.2617

Max Act: 2.9678. Min Act: -0.1700

Data Index: 4230485 (Open Web Text)

Max Activating Token Index: 28

Text #6

Max Range: 3.2617. Min Range: -3.2617

Max Act: 2.9489. Min Act: -0.1700

Data Index: 6772352 (Open Web Text)

Max Activating Token Index: 896

Text #7

Max Range: 3.2617. Min Range: -3.2617

Max Act: 2.9435. Min Act: -0.1700

Data Index: 1021803 (Open Web Text)

Max Activating Token Index: 169

Text #8

Max Range: 3.2617. Min Range: -3.2617

Max Act: 2.9535. Min Act: -0.1700

Data Index: 1487643 (Open Web Text)

Max Activating Token Index: 525

Text #9

Max Range: 3.2617. Min Range: -3.2617

Max Act: 2.9431. Min Act: -0.1700

Data Index: 3256520 (Open Web Text)

Max Activating Token Index: 868

Text #10

Max Range: 3.2617. Min Range: -3.2617

Max Act: 2.9532. Min Act: -0.1700

Data Index: 4596449 (Open Web Text)

Max Activating Token Index: 560

Text #11

Max Range: 3.2617. Min Range: -3.2617

Max Act: 2.9353. Min Act: -0.1700

Data Index: 2598325 (Open Web Text)

Max Activating Token Index: 545

Text #12

Max Range: 3.2617. Min Range: -3.2617

Max Act: 2.8896. Min Act: -0.1700

Data Index: 203241 (Open Web Text)

Max Activating Token Index: 388

Text #13

Max Range: 3.2617. Min Range: -3.2617

Max Act: 2.9056. Min Act: -0.1700

Data Index: 18964 (Open Web Text)

Max Activating Token Index: 790

Text #14

Max Range: 3.2617. Min Range: -3.2617

Max Act: 2.8989. Min Act: -0.1700

Data Index: 4008671 (Open Web Text)

Max Activating Token Index: 804

Text #15

Max Range: 3.2617. Min Range: -3.2617

Max Act: 2.8922. Min Act: -0.1700

Data Index: 6441734 (Open Web Text)

Max Activating Token Index: 762

Text #16

Max Range: 3.2617. Min Range: -3.2617

Max Act: 2.8741. Min Act: -0.1700

Data Index: 1115470 (Open Web Text)

Max Activating Token Index: 987

Text #17

Max Range: 3.2617. Min Range: -3.2617

Max Act: 2.9034. Min Act: -0.1700

Data Index: 6536264 (Open Web Text)

Max Activating Token Index: 830

Text #18

Max Range: 3.2617. Min Range: -3.2617

Max Act: 2.8701. Min Act: -0.1700

Data Index: 5706932 (Open Web Text)

Max Activating Token Index: 477

Text #19

Max Range: 3.2617. Min Range: -3.2617

Max Act: 2.8590. Min Act: -0.1700

Data Index: 7523758 (Open Web Text)

Max Activating Token Index: 453