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

Dataset: Open Web Text

Neuron 1898 in Layer 4

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: 3.9802. Min Range: -3.9802

Max Act: 3.9781. Min Act: -0.1700

Data Index: 1067841 (Open Web Text)

Max Activating Token Index: 38

Text #1

Max Range: 3.9802. Min Range: -3.9802

Max Act: 3.9802. Min Act: -0.1700

Data Index: 1682951 (Open Web Text)

Max Activating Token Index: 159

Text #2

Max Range: 3.9802. Min Range: -3.9802

Max Act: 3.9697. Min Act: -0.1700

Data Index: 2544917 (Open Web Text)

Max Activating Token Index: 366

Text #3

Max Range: 3.9802. Min Range: -3.9802

Max Act: 3.9611. Min Act: -0.1700

Data Index: 2376687 (Open Web Text)

Max Activating Token Index: 426

Text #4

Max Range: 3.9802. Min Range: -3.9802

Max Act: 3.9232. Min Act: -0.1700

Data Index: 7673371 (Open Web Text)

Max Activating Token Index: 119

Text #5

Max Range: 3.9802. Min Range: -3.9802

Max Act: 3.8940. Min Act: -0.1700

Data Index: 4364528 (Open Web Text)

Max Activating Token Index: 830

Text #6

Max Range: 3.9802. Min Range: -3.9802

Max Act: 3.8935. Min Act: -0.1700

Data Index: 1670418 (Open Web Text)

Max Activating Token Index: 977

Text #7

Max Range: 3.9802. Min Range: -3.9802

Max Act: 3.9004. Min Act: -0.1700

Data Index: 2420904 (Open Web Text)

Max Activating Token Index: 980

Text #8

Max Range: 3.9802. Min Range: -3.9802

Max Act: 3.8964. Min Act: -0.1700

Data Index: 7793049 (Open Web Text)

Max Activating Token Index: 937

Text #9

Max Range: 3.9802. Min Range: -3.9802

Max Act: 3.8727. Min Act: -0.1700

Data Index: 7247509 (Open Web Text)

Max Activating Token Index: 932

Text #10

Max Range: 3.9802. Min Range: -3.9802

Max Act: 3.8698. Min Act: -0.1700

Data Index: 535540 (Open Web Text)

Max Activating Token Index: 578

Text #11

Max Range: 3.9802. Min Range: -3.9802

Max Act: 3.8332. Min Act: -0.1700

Data Index: 8151619 (Open Web Text)

Max Activating Token Index: 567

Text #12

Max Range: 3.9802. Min Range: -3.9802

Max Act: 3.8315. Min Act: -0.1700

Data Index: 6970762 (Open Web Text)

Max Activating Token Index: 169

Text #13

Max Range: 3.9802. Min Range: -3.9802

Max Act: 3.8586. Min Act: -0.1700

Data Index: 8431465 (Open Web Text)

Max Activating Token Index: 269

Text #14

Max Range: 3.9802. Min Range: -3.9802

Max Act: 3.8543. Min Act: -0.1700

Data Index: 2322264 (Open Web Text)

Max Activating Token Index: 368

Text #15

Max Range: 3.9802. Min Range: -3.9802

Max Act: 3.8489. Min Act: -0.1700

Data Index: 6151706 (Open Web Text)

Max Activating Token Index: 779

Text #16

Max Range: 3.9802. Min Range: -3.9802

Max Act: 3.8418. Min Act: -0.1700

Data Index: 2269112 (Open Web Text)

Max Activating Token Index: 376

Text #17

Max Range: 3.9802. Min Range: -3.9802

Max Act: 3.8358. Min Act: -0.1700

Data Index: 4167880 (Open Web Text)

Max Activating Token Index: 117

Text #18

Max Range: 3.9802. Min Range: -3.9802

Max Act: 3.8171. Min Act: -0.1700

Data Index: 4748344 (Open Web Text)

Max Activating Token Index: 813

Text #19

Max Range: 3.9802. Min Range: -3.9802

Max Act: 3.7925. Min Act: -0.1700

Data Index: 715848 (Open Web Text)

Max Activating Token Index: 970