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

Dataset: Open Web Text

Neuron 1650 in Layer 6

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: 4.0504. Min Range: -4.0504

Max Act: 4.0504. Min Act: -0.1700

Data Index: 5536395 (Open Web Text)

Max Activating Token Index: 639

Text #1

Max Range: 4.0504. Min Range: -4.0504

Max Act: 4.0129. Min Act: -0.1700

Data Index: 8361262 (Open Web Text)

Max Activating Token Index: 440

Text #2

Max Range: 4.0504. Min Range: -4.0504

Max Act: 4.0073. Min Act: -0.1700

Data Index: 5216570 (Open Web Text)

Max Activating Token Index: 480

Text #3

Max Range: 4.0504. Min Range: -4.0504

Max Act: 3.9183. Min Act: -0.1700

Data Index: 4419050 (Open Web Text)

Max Activating Token Index: 447

Text #4

Max Range: 4.0504. Min Range: -4.0504

Max Act: 3.9360. Min Act: -0.1700

Data Index: 5622761 (Open Web Text)

Max Activating Token Index: 720

Text #5

Max Range: 4.0504. Min Range: -4.0504

Max Act: 3.8997. Min Act: -0.1700

Data Index: 62971 (Open Web Text)

Max Activating Token Index: 340

Text #6

Max Range: 4.0504. Min Range: -4.0504

Max Act: 3.8497. Min Act: -0.1700

Data Index: 162934 (Open Web Text)

Max Activating Token Index: 813

Text #7

Max Range: 4.0504. Min Range: -4.0504

Max Act: 3.8850. Min Act: -0.1700

Data Index: 694095 (Open Web Text)

Max Activating Token Index: 465

Text #8

Max Range: 4.0504. Min Range: -4.0504

Max Act: 3.8833. Min Act: -0.1700

Data Index: 4845592 (Open Web Text)

Max Activating Token Index: 471

Text #9

Max Range: 4.0504. Min Range: -4.0504

Max Act: 3.8986. Min Act: -0.1700

Data Index: 124289 (Open Web Text)

Max Activating Token Index: 199

Text #10

Max Range: 4.0504. Min Range: -4.0504

Max Act: 3.8580. Min Act: -0.1700

Data Index: 7981469 (Open Web Text)

Max Activating Token Index: 32

Text #11

Max Range: 4.0504. Min Range: -4.0504

Max Act: 3.8624. Min Act: -0.1700

Data Index: 1128550 (Open Web Text)

Max Activating Token Index: 554

Text #12

Max Range: 4.0504. Min Range: -4.0504

Max Act: 3.8458. Min Act: -0.1700

Data Index: 3343289 (Open Web Text)

Max Activating Token Index: 145

Text #13

Max Range: 4.0504. Min Range: -4.0504

Max Act: 3.8443. Min Act: -0.1700

Data Index: 1383086 (Open Web Text)

Max Activating Token Index: 865

Text #14

Max Range: 4.0504. Min Range: -4.0504

Max Act: 3.8596. Min Act: -0.1700

Data Index: 8385672 (Open Web Text)

Max Activating Token Index: 26

Text #15

Max Range: 4.0504. Min Range: -4.0504

Max Act: 3.8277. Min Act: -0.1700

Data Index: 6886460 (Open Web Text)

Max Activating Token Index: 961

Text #16

Max Range: 4.0504. Min Range: -4.0504

Max Act: 3.7913. Min Act: -0.1700

Data Index: 1745581 (Open Web Text)

Max Activating Token Index: 784

Text #17

Max Range: 4.0504. Min Range: -4.0504

Max Act: 3.8121. Min Act: -0.1700

Data Index: 6797729 (Open Web Text)

Max Activating Token Index: 669

Text #18

Max Range: 4.0504. Min Range: -4.0504

Max Act: 3.8164. Min Act: -0.1700

Data Index: 2375374 (Open Web Text)

Max Activating Token Index: 647

Text #19

Max Range: 4.0504. Min Range: -4.0504

Max Act: 3.8161. Min Act: -0.1700

Data Index: 5889360 (Open Web Text)

Max Activating Token Index: 67