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

Dataset: Open Web Text

Neuron 767 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: 4.3841. Min Range: -4.3841

Max Act: 4.3484. Min Act: -0.1700

Data Index: 8687620 (Open Web Text)

Max Activating Token Index: 590

Text #1

Max Range: 4.3841. Min Range: -4.3841

Max Act: 4.3610. Min Act: -0.1700

Data Index: 8823691 (Open Web Text)

Max Activating Token Index: 359

Text #2

Max Range: 4.3841. Min Range: -4.3841

Max Act: 4.3304. Min Act: -0.1700

Data Index: 7249040 (Open Web Text)

Max Activating Token Index: 762

Text #3

Max Range: 4.3841. Min Range: -4.3841

Max Act: 4.3675. Min Act: -0.1700

Data Index: 3318678 (Open Web Text)

Max Activating Token Index: 827

Text #4

Max Range: 4.3841. Min Range: -4.3841

Max Act: 4.2901. Min Act: -0.1700

Data Index: 3216073 (Open Web Text)

Max Activating Token Index: 680

Text #5

Max Range: 4.3841. Min Range: -4.3841

Max Act: 4.3497. Min Act: -0.1700

Data Index: 8481881 (Open Web Text)

Max Activating Token Index: 837

Text #6

Max Range: 4.3841. Min Range: -4.3841

Max Act: 4.3473. Min Act: -0.1700

Data Index: 5419836 (Open Web Text)

Max Activating Token Index: 545

Text #7

Max Range: 4.3841. Min Range: -4.3841

Max Act: 4.3472. Min Act: -0.1700

Data Index: 2884144 (Open Web Text)

Max Activating Token Index: 384

Text #8

Max Range: 4.3841. Min Range: -4.3841

Max Act: 4.3841. Min Act: -0.1700

Data Index: 1036931 (Open Web Text)

Max Activating Token Index: 451

Text #9

Max Range: 4.3841. Min Range: -4.3841

Max Act: 4.2793. Min Act: -0.1700

Data Index: 3503941 (Open Web Text)

Max Activating Token Index: 617

Text #10

Max Range: 4.3841. Min Range: -4.3841

Max Act: 4.2970. Min Act: -0.1700

Data Index: 2264196 (Open Web Text)

Max Activating Token Index: 39

Text #11

Max Range: 4.3841. Min Range: -4.3841

Max Act: 4.3115. Min Act: -0.1700

Data Index: 7365271 (Open Web Text)

Max Activating Token Index: 431

Text #12

Max Range: 4.3841. Min Range: -4.3841

Max Act: 4.2714. Min Act: -0.1700

Data Index: 4968238 (Open Web Text)

Max Activating Token Index: 768

Text #13

Max Range: 4.3841. Min Range: -4.3841

Max Act: 4.2960. Min Act: -0.1700

Data Index: 1426696 (Open Web Text)

Max Activating Token Index: 786

Text #14

Max Range: 4.3841. Min Range: -4.3841

Max Act: 4.2825. Min Act: -0.1700

Data Index: 3160361 (Open Web Text)

Max Activating Token Index: 91

Text #15

Max Range: 4.3841. Min Range: -4.3841

Max Act: 4.2354. Min Act: -0.1700

Data Index: 7312163 (Open Web Text)

Max Activating Token Index: 471

Text #16

Max Range: 4.3841. Min Range: -4.3841

Max Act: 4.2416. Min Act: -0.1700

Data Index: 5080593 (Open Web Text)

Max Activating Token Index: 671

Text #17

Max Range: 4.3841. Min Range: -4.3841

Max Act: 4.2711. Min Act: -0.1700

Data Index: 3016657 (Open Web Text)

Max Activating Token Index: 893

Text #18

Max Range: 4.3841. Min Range: -4.3841

Max Act: 4.2204. Min Act: -0.1700

Data Index: 7857126 (Open Web Text)

Max Activating Token Index: 842

Text #19

Max Range: 4.3841. Min Range: -4.3841

Max Act: 4.2498. Min Act: -0.1700

Data Index: 1788757 (Open Web Text)

Max Activating Token Index: 346