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

Dataset: Open Web Text

Neuron 240 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: 4.9504. Min Range: -4.9504

Max Act: 4.9504. Min Act: -0.1700

Data Index: 5327975 (Open Web Text)

Max Activating Token Index: 700

Text #1

Max Range: 4.9504. Min Range: -4.9504

Max Act: 4.8841. Min Act: -0.1700

Data Index: 3652516 (Open Web Text)

Max Activating Token Index: 999

Text #2

Max Range: 4.9504. Min Range: -4.9504

Max Act: 4.8904. Min Act: -0.1700

Data Index: 7255749 (Open Web Text)

Max Activating Token Index: 588

Text #3

Max Range: 4.9504. Min Range: -4.9504

Max Act: 4.8535. Min Act: -0.1700

Data Index: 4341309 (Open Web Text)

Max Activating Token Index: 376

Text #4

Max Range: 4.9504. Min Range: -4.9504

Max Act: 4.8460. Min Act: -0.1700

Data Index: 5441436 (Open Web Text)

Max Activating Token Index: 497

Text #5

Max Range: 4.9504. Min Range: -4.9504

Max Act: 4.8623. Min Act: -0.1700

Data Index: 5824807 (Open Web Text)

Max Activating Token Index: 494

Text #6

Max Range: 4.9504. Min Range: -4.9504

Max Act: 4.8452. Min Act: -0.1700

Data Index: 15294 (Open Web Text)

Max Activating Token Index: 967

Text #7

Max Range: 4.9504. Min Range: -4.9504

Max Act: 4.8260. Min Act: -0.1700

Data Index: 5516885 (Open Web Text)

Max Activating Token Index: 430

Text #8

Max Range: 4.9504. Min Range: -4.9504

Max Act: 4.8253. Min Act: -0.1700

Data Index: 1734494 (Open Web Text)

Max Activating Token Index: 565

Text #9

Max Range: 4.9504. Min Range: -4.9504

Max Act: 4.7967. Min Act: -0.1700

Data Index: 1495626 (Open Web Text)

Max Activating Token Index: 522

Text #10

Max Range: 4.9504. Min Range: -4.9504

Max Act: 4.7848. Min Act: -0.1700

Data Index: 4008919 (Open Web Text)

Max Activating Token Index: 470

Text #11

Max Range: 4.9504. Min Range: -4.9504

Max Act: 4.8139. Min Act: -0.1700

Data Index: 8418815 (Open Web Text)

Max Activating Token Index: 1001

Text #12

Max Range: 4.9504. Min Range: -4.9504

Max Act: 4.8168. Min Act: -0.1700

Data Index: 2047091 (Open Web Text)

Max Activating Token Index: 726

Text #13

Max Range: 4.9504. Min Range: -4.9504

Max Act: 4.7796. Min Act: -0.1700

Data Index: 1159153 (Open Web Text)

Max Activating Token Index: 328

Text #14

Max Range: 4.9504. Min Range: -4.9504

Max Act: 4.7998. Min Act: -0.1700

Data Index: 8353356 (Open Web Text)

Max Activating Token Index: 575

Text #15

Max Range: 4.9504. Min Range: -4.9504

Max Act: 4.7820. Min Act: -0.1700

Data Index: 7955985 (Open Web Text)

Max Activating Token Index: 907

Text #16

Max Range: 4.9504. Min Range: -4.9504

Max Act: 4.8145. Min Act: -0.1700

Data Index: 6616406 (Open Web Text)

Max Activating Token Index: 362

Text #17

Max Range: 4.9504. Min Range: -4.9504

Max Act: 4.7995. Min Act: -0.1700

Data Index: 6160683 (Open Web Text)

Max Activating Token Index: 123

Text #18

Max Range: 4.9504. Min Range: -4.9504

Max Act: 4.7901. Min Act: -0.1700

Data Index: 1758384 (Open Web Text)

Max Activating Token Index: 673

Text #19

Max Range: 4.9504. Min Range: -4.9504

Max Act: 4.7908. Min Act: -0.1700

Data Index: 2455220 (Open Web Text)

Max Activating Token Index: 796