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

Dataset: Open Web Text

Neuron 482 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: 3.1552. Min Range: -3.1552

Max Act: 3.1552. Min Act: -0.1700

Data Index: 1008814 (Open Web Text)

Max Activating Token Index: 34

Text #1

Max Range: 3.1552. Min Range: -3.1552

Max Act: 3.0756. Min Act: -0.1700

Data Index: 7226916 (Open Web Text)

Max Activating Token Index: 888

Text #2

Max Range: 3.1552. Min Range: -3.1552

Max Act: 3.0422. Min Act: -0.1700

Data Index: 642028 (Open Web Text)

Max Activating Token Index: 661

Text #3

Max Range: 3.1552. Min Range: -3.1552

Max Act: 3.0294. Min Act: -0.1700

Data Index: 4305575 (Open Web Text)

Max Activating Token Index: 49

Text #4

Max Range: 3.1552. Min Range: -3.1552

Max Act: 3.0232. Min Act: -0.1700

Data Index: 7567258 (Open Web Text)

Max Activating Token Index: 933

Text #5

Max Range: 3.1552. Min Range: -3.1552

Max Act: 3.0164. Min Act: -0.1700

Data Index: 3982122 (Open Web Text)

Max Activating Token Index: 712

Text #6

Max Range: 3.1552. Min Range: -3.1552

Max Act: 3.0171. Min Act: -0.1700

Data Index: 1931126 (Open Web Text)

Max Activating Token Index: 335

Text #7

Max Range: 3.1552. Min Range: -3.1552

Max Act: 3.0097. Min Act: -0.1700

Data Index: 6770042 (Open Web Text)

Max Activating Token Index: 510

Text #8

Max Range: 3.1552. Min Range: -3.1552

Max Act: 3.0123. Min Act: -0.1700

Data Index: 3558732 (Open Web Text)

Max Activating Token Index: 136

Text #9

Max Range: 3.1552. Min Range: -3.1552

Max Act: 3.0128. Min Act: -0.1700

Data Index: 3125739 (Open Web Text)

Max Activating Token Index: 150

Text #10

Max Range: 3.1552. Min Range: -3.1552

Max Act: 3.0022. Min Act: -0.1700

Data Index: 6498654 (Open Web Text)

Max Activating Token Index: 145

Text #11

Max Range: 3.1552. Min Range: -3.1552

Max Act: 3.0044. Min Act: -0.1700

Data Index: 4224787 (Open Web Text)

Max Activating Token Index: 327

Text #12

Max Range: 3.1552. Min Range: -3.1552

Max Act: 2.9582. Min Act: -0.1700

Data Index: 6914395 (Open Web Text)

Max Activating Token Index: 485

Text #13

Max Range: 3.1552. Min Range: -3.1552

Max Act: 2.9779. Min Act: -0.1700

Data Index: 8578570 (Open Web Text)

Max Activating Token Index: 154

Text #14

Max Range: 3.1552. Min Range: -3.1552

Max Act: 2.9674. Min Act: -0.1700

Data Index: 841172 (Open Web Text)

Max Activating Token Index: 79

Text #15

Max Range: 3.1552. Min Range: -3.1552

Max Act: 2.9714. Min Act: -0.1700

Data Index: 8308363 (Open Web Text)

Max Activating Token Index: 362

Text #16

Max Range: 3.1552. Min Range: -3.1552

Max Act: 2.9715. Min Act: -0.1700

Data Index: 4453014 (Open Web Text)

Max Activating Token Index: 588

Text #17

Max Range: 3.1552. Min Range: -3.1552

Max Act: 2.9496. Min Act: -0.1700

Data Index: 7604876 (Open Web Text)

Max Activating Token Index: 1022

Text #18

Max Range: 3.1552. Min Range: -3.1552

Max Act: 2.9676. Min Act: -0.1700

Data Index: 2415520 (Open Web Text)

Max Activating Token Index: 166

Text #19

Max Range: 3.1552. Min Range: -3.1552

Max Act: 2.9787. Min Act: -0.1700

Data Index: 6591872 (Open Web Text)

Max Activating Token Index: 71