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

Dataset: Open Web Text

Neuron 2998 in Layer 1

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: 2.0574. Min Range: -2.0574

Max Act: 2.0574. Min Act: -0.1700

Data Index: 2569424 (Open Web Text)

Max Activating Token Index: 586

Text #1

Max Range: 2.0574. Min Range: -2.0574

Max Act: 2.0467. Min Act: -0.1699

Data Index: 1846206 (Open Web Text)

Max Activating Token Index: 211

Text #2

Max Range: 2.0574. Min Range: -2.0574

Max Act: 2.0452. Min Act: -0.1700

Data Index: 5758229 (Open Web Text)

Max Activating Token Index: 642

Text #3

Max Range: 2.0574. Min Range: -2.0574

Max Act: 2.0385. Min Act: -0.1700

Data Index: 4248822 (Open Web Text)

Max Activating Token Index: 702

Text #4

Max Range: 2.0574. Min Range: -2.0574

Max Act: 2.0445. Min Act: -0.1700

Data Index: 6911710 (Open Web Text)

Max Activating Token Index: 532

Text #5

Max Range: 2.0574. Min Range: -2.0574

Max Act: 2.0283. Min Act: -0.1700

Data Index: 8231071 (Open Web Text)

Max Activating Token Index: 502

Text #6

Max Range: 2.0574. Min Range: -2.0574

Max Act: 2.0215. Min Act: -0.1700

Data Index: 4760768 (Open Web Text)

Max Activating Token Index: 549

Text #7

Max Range: 2.0574. Min Range: -2.0574

Max Act: 2.0210. Min Act: -0.1700

Data Index: 4233636 (Open Web Text)

Max Activating Token Index: 736

Text #8

Max Range: 2.0574. Min Range: -2.0574

Max Act: 2.0201. Min Act: -0.1700

Data Index: 6092300 (Open Web Text)

Max Activating Token Index: 369

Text #9

Max Range: 2.0574. Min Range: -2.0574

Max Act: 2.0108. Min Act: -0.1700

Data Index: 4056188 (Open Web Text)

Max Activating Token Index: 176

Text #10

Max Range: 2.0574. Min Range: -2.0574

Max Act: 2.0127. Min Act: -0.1700

Data Index: 7765915 (Open Web Text)

Max Activating Token Index: 505

Text #11

Max Range: 2.0574. Min Range: -2.0574

Max Act: 2.0034. Min Act: -0.1700

Data Index: 604164 (Open Web Text)

Max Activating Token Index: 126

Text #12

Max Range: 2.0574. Min Range: -2.0574

Max Act: 1.9802. Min Act: -0.1700

Data Index: 4464429 (Open Web Text)

Max Activating Token Index: 362

Text #13

Max Range: 2.0574. Min Range: -2.0574

Max Act: 1.9880. Min Act: -0.1700

Data Index: 3538965 (Open Web Text)

Max Activating Token Index: 326

Text #14

Max Range: 2.0574. Min Range: -2.0574

Max Act: 1.9872. Min Act: -0.1700

Data Index: 5942725 (Open Web Text)

Max Activating Token Index: 394

Text #15

Max Range: 2.0574. Min Range: -2.0574

Max Act: 1.9900. Min Act: -0.1700

Data Index: 4726428 (Open Web Text)

Max Activating Token Index: 271

Text #16

Max Range: 2.0574. Min Range: -2.0574

Max Act: 1.9921. Min Act: -0.1700

Data Index: 649334 (Open Web Text)

Max Activating Token Index: 700

Text #17

Max Range: 2.0574. Min Range: -2.0574

Max Act: 1.9797. Min Act: -0.1700

Data Index: 5673720 (Open Web Text)

Max Activating Token Index: 616

Text #18

Max Range: 2.0574. Min Range: -2.0574

Max Act: 1.9984. Min Act: -0.1700

Data Index: 8064145 (Open Web Text)

Max Activating Token Index: 412

Text #19

Max Range: 2.0574. Min Range: -2.0574

Max Act: 1.9992. Min Act: -0.1700

Data Index: 5748186 (Open Web Text)

Max Activating Token Index: 79