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

Dataset: Open Web Text

Neuron 1697 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: 3.7198. Min Range: -3.7198

Max Act: 3.7198. Min Act: -0.1700

Data Index: 519971 (Open Web Text)

Max Activating Token Index: 751

Text #1

Max Range: 3.7198. Min Range: -3.7198

Max Act: 3.6739. Min Act: -0.1700

Data Index: 2466896 (Open Web Text)

Max Activating Token Index: 289

Text #2

Max Range: 3.7198. Min Range: -3.7198

Max Act: 3.6005. Min Act: -0.1700

Data Index: 7333036 (Open Web Text)

Max Activating Token Index: 304

Text #3

Max Range: 3.7198. Min Range: -3.7198

Max Act: 3.6141. Min Act: -0.1700

Data Index: 5212737 (Open Web Text)

Max Activating Token Index: 680

Text #4

Max Range: 3.7198. Min Range: -3.7198

Max Act: 3.6192. Min Act: -0.1700

Data Index: 3451695 (Open Web Text)

Max Activating Token Index: 793

Text #5

Max Range: 3.7198. Min Range: -3.7198

Max Act: 3.6142. Min Act: -0.1700

Data Index: 1326625 (Open Web Text)

Max Activating Token Index: 145

Text #6

Max Range: 3.7198. Min Range: -3.7198

Max Act: 3.6164. Min Act: -0.1700

Data Index: 2889122 (Open Web Text)

Max Activating Token Index: 603

Text #7

Max Range: 3.7198. Min Range: -3.7198

Max Act: 3.6068. Min Act: -0.1700

Data Index: 4710813 (Open Web Text)

Max Activating Token Index: 40

Text #8

Max Range: 3.7198. Min Range: -3.7198

Max Act: 3.6058. Min Act: -0.1700

Data Index: 7071034 (Open Web Text)

Max Activating Token Index: 514

Text #9

Max Range: 3.7198. Min Range: -3.7198

Max Act: 3.5923. Min Act: -0.1700

Data Index: 2213613 (Open Web Text)

Max Activating Token Index: 220

Text #10

Max Range: 3.7198. Min Range: -3.7198

Max Act: 3.5943. Min Act: -0.1700

Data Index: 7064271 (Open Web Text)

Max Activating Token Index: 191

Text #11

Max Range: 3.7198. Min Range: -3.7198

Max Act: 3.5934. Min Act: -0.1700

Data Index: 5287578 (Open Web Text)

Max Activating Token Index: 58

Text #12

Max Range: 3.7198. Min Range: -3.7198

Max Act: 3.5640. Min Act: -0.1700

Data Index: 3376323 (Open Web Text)

Max Activating Token Index: 937

Text #13

Max Range: 3.7198. Min Range: -3.7198

Max Act: 3.5672. Min Act: -0.1700

Data Index: 4170817 (Open Web Text)

Max Activating Token Index: 218

Text #14

Max Range: 3.7198. Min Range: -3.7198

Max Act: 3.5904. Min Act: -0.1700

Data Index: 8824568 (Open Web Text)

Max Activating Token Index: 691

Text #15

Max Range: 3.7198. Min Range: -3.7198

Max Act: 3.5531. Min Act: -0.1700

Data Index: 5213205 (Open Web Text)

Max Activating Token Index: 141

Text #16

Max Range: 3.7198. Min Range: -3.7198

Max Act: 3.5656. Min Act: -0.1700

Data Index: 3360936 (Open Web Text)

Max Activating Token Index: 581

Text #17

Max Range: 3.7198. Min Range: -3.7198

Max Act: 3.5486. Min Act: -0.1700

Data Index: 2844708 (Open Web Text)

Max Activating Token Index: 447

Text #18

Max Range: 3.7198. Min Range: -3.7198

Max Act: 3.5335. Min Act: -0.1700

Data Index: 3536631 (Open Web Text)

Max Activating Token Index: 925

Text #19

Max Range: 3.7198. Min Range: -3.7198

Max Act: 3.5437. Min Act: -0.1700

Data Index: 4791157 (Open Web Text)

Max Activating Token Index: 888