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

Dataset: Open Web Text

Neuron 2944 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: 3.5070. Min Range: -3.5070

Max Act: 3.5070. Min Act: -0.1700

Data Index: 244576 (Open Web Text)

Max Activating Token Index: 43

Text #1

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.4094. Min Act: -0.1700

Data Index: 3646729 (Open Web Text)

Max Activating Token Index: 250

Text #2

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.3506. Min Act: -0.1700

Data Index: 2899509 (Open Web Text)

Max Activating Token Index: 568

Text #3

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.3501. Min Act: -0.1700

Data Index: 5978792 (Open Web Text)

Max Activating Token Index: 145

Text #4

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.3081. Min Act: -0.1700

Data Index: 6454856 (Open Web Text)

Max Activating Token Index: 321

Text #5

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.3453. Min Act: -0.1700

Data Index: 6802798 (Open Web Text)

Max Activating Token Index: 723

Text #6

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.2955. Min Act: -0.1700

Data Index: 6485995 (Open Web Text)

Max Activating Token Index: 170

Text #7

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.2882. Min Act: -0.1700

Data Index: 2546344 (Open Web Text)

Max Activating Token Index: 770

Text #8

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.2821. Min Act: -0.1700

Data Index: 1195403 (Open Web Text)

Max Activating Token Index: 241

Text #9

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.2840. Min Act: -0.1700

Data Index: 1830490 (Open Web Text)

Max Activating Token Index: 994

Text #10

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.2619. Min Act: -0.1700

Data Index: 487872 (Open Web Text)

Max Activating Token Index: 605

Text #11

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.2851. Min Act: -0.1700

Data Index: 8064773 (Open Web Text)

Max Activating Token Index: 435

Text #12

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.2977. Min Act: -0.1700

Data Index: 1683317 (Open Web Text)

Max Activating Token Index: 902

Text #13

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.2702. Min Act: -0.1700

Data Index: 2038141 (Open Web Text)

Max Activating Token Index: 491

Text #14

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.2633. Min Act: -0.1700

Data Index: 5405689 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.2742. Min Act: -0.1700

Data Index: 8109450 (Open Web Text)

Max Activating Token Index: 498

Text #16

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.2587. Min Act: -0.1700

Data Index: 8346833 (Open Web Text)

Max Activating Token Index: 414

Text #17

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.2468. Min Act: -0.1700

Data Index: 4724965 (Open Web Text)

Max Activating Token Index: 434

Text #18

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.2577. Min Act: -0.1700

Data Index: 184052 (Open Web Text)

Max Activating Token Index: 354

Text #19

Max Range: 3.5070. Min Range: -3.5070

Max Act: 3.2509. Min Act: -0.1700

Data Index: 1097865 (Open Web Text)

Max Activating Token Index: 126