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

Dataset: Open Web Text

Neuron 1098 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: 3.7658. Min Range: -3.7658

Max Act: 3.7658. Min Act: -0.1700

Data Index: 5726556 (Open Web Text)

Max Activating Token Index: 902

Text #1

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.6889. Min Act: -0.1700

Data Index: 5165391 (Open Web Text)

Max Activating Token Index: 724

Text #2

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.6542. Min Act: -0.1700

Data Index: 1572674 (Open Web Text)

Max Activating Token Index: 217

Text #3

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.6814. Min Act: -0.1700

Data Index: 5412252 (Open Web Text)

Max Activating Token Index: 997

Text #4

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.5794. Min Act: -0.1700

Data Index: 3501071 (Open Web Text)

Max Activating Token Index: 749

Text #5

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.5827. Min Act: -0.1700

Data Index: 3266574 (Open Web Text)

Max Activating Token Index: 296

Text #6

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.5660. Min Act: -0.1700

Data Index: 162358 (Open Web Text)

Max Activating Token Index: 271

Text #7

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.5699. Min Act: -0.1700

Data Index: 620396 (Open Web Text)

Max Activating Token Index: 997

Text #8

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.5617. Min Act: -0.1700

Data Index: 6723920 (Open Web Text)

Max Activating Token Index: 624

Text #9

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.5208. Min Act: -0.1700

Data Index: 572768 (Open Web Text)

Max Activating Token Index: 364

Text #10

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.5038. Min Act: -0.1700

Data Index: 5255659 (Open Web Text)

Max Activating Token Index: 19

Text #11

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.4852. Min Act: -0.1700

Data Index: 5094442 (Open Web Text)

Max Activating Token Index: 220

Text #12

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.4942. Min Act: -0.1700

Data Index: 3049549 (Open Web Text)

Max Activating Token Index: 671

Text #13

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.4601. Min Act: -0.1700

Data Index: 5347464 (Open Web Text)

Max Activating Token Index: 183

Text #14

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.4570. Min Act: -0.1700

Data Index: 4465213 (Open Web Text)

Max Activating Token Index: 48

Text #15

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.5043. Min Act: -0.1700

Data Index: 3266890 (Open Web Text)

Max Activating Token Index: 914

Text #16

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.4665. Min Act: -0.1700

Data Index: 6877280 (Open Web Text)

Max Activating Token Index: 144

Text #17

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.4594. Min Act: -0.1700

Data Index: 7663969 (Open Web Text)

Max Activating Token Index: 933

Text #18

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.4704. Min Act: -0.1700

Data Index: 2771951 (Open Web Text)

Max Activating Token Index: 145

Text #19

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.4816. Min Act: -0.1700

Data Index: 2228947 (Open Web Text)

Max Activating Token Index: 931