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

Dataset: Open Web Text

Neuron 2794 in Layer 1

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: 1.8565. Min Range: -1.8565

Max Act: 1.8565. Min Act: -0.1699

Data Index: 7527180 (Open Web Text)

Max Activating Token Index: 29

Text #1

Max Range: 1.8565. Min Range: -1.8565

Max Act: 1.8380. Min Act: -0.1700

Data Index: 1528670 (Open Web Text)

Max Activating Token Index: 407

Text #2

Max Range: 1.8565. Min Range: -1.8565

Max Act: 1.8268. Min Act: -0.1700

Data Index: 6141884 (Open Web Text)

Max Activating Token Index: 284

Text #3

Max Range: 1.8565. Min Range: -1.8565

Max Act: 1.8214. Min Act: -0.1700

Data Index: 7975 (Open Web Text)

Max Activating Token Index: 280

Text #4

Max Range: 1.8565. Min Range: -1.8565

Max Act: 1.7942. Min Act: -0.1700

Data Index: 6998737 (Open Web Text)

Max Activating Token Index: 152

Text #5

Max Range: 1.8565. Min Range: -1.8565

Max Act: 1.7746. Min Act: -0.1700

Data Index: 2906988 (Open Web Text)

Max Activating Token Index: 226

Text #6

Max Range: 1.8565. Min Range: -1.8565

Max Act: 1.7780. Min Act: -0.1700

Data Index: 1787909 (Open Web Text)

Max Activating Token Index: 73

Text #7

Max Range: 1.8565. Min Range: -1.8565

Max Act: 1.7751. Min Act: -0.1700

Data Index: 78908 (Open Web Text)

Max Activating Token Index: 157

Text #8

Max Range: 1.8565. Min Range: -1.8565

Max Act: 1.7840. Min Act: -0.1700

Data Index: 940091 (Open Web Text)

Max Activating Token Index: 818

Text #9

Max Range: 1.8565. Min Range: -1.8565

Max Act: 1.7781. Min Act: -0.1700

Data Index: 7952761 (Open Web Text)

Max Activating Token Index: 520

Text #10

Max Range: 1.8565. Min Range: -1.8565

Max Act: 1.7705. Min Act: -0.1700

Data Index: 270109 (Open Web Text)

Max Activating Token Index: 527

Text #11

Max Range: 1.8565. Min Range: -1.8565

Max Act: 1.7694. Min Act: -0.1700

Data Index: 8677054 (Open Web Text)

Max Activating Token Index: 491

Text #12

Max Range: 1.8565. Min Range: -1.8565

Max Act: 1.7679. Min Act: -0.1700

Data Index: 6932763 (Open Web Text)

Max Activating Token Index: 311

Text #13

Max Range: 1.8565. Min Range: -1.8565

Max Act: 1.7687. Min Act: -0.1700

Data Index: 1220438 (Open Web Text)

Max Activating Token Index: 325

Text #14

Max Range: 1.8565. Min Range: -1.8565

Max Act: 1.7609. Min Act: -0.1700

Data Index: 5894801 (Open Web Text)

Max Activating Token Index: 838

Text #15

Max Range: 1.8565. Min Range: -1.8565

Max Act: 1.7686. Min Act: -0.1700

Data Index: 106459 (Open Web Text)

Max Activating Token Index: 866

Text #16

Max Range: 1.8565. Min Range: -1.8565

Max Act: 1.7562. Min Act: -0.1700

Data Index: 3524372 (Open Web Text)

Max Activating Token Index: 873

Text #17

Max Range: 1.8565. Min Range: -1.8565

Max Act: 1.7497. Min Act: -0.1700

Data Index: 6932761 (Open Web Text)

Max Activating Token Index: 662

Text #18

Max Range: 1.8565. Min Range: -1.8565

Max Act: 1.7548. Min Act: -0.1700

Data Index: 555453 (Open Web Text)

Max Activating Token Index: 222

Text #19

Max Range: 1.8565. Min Range: -1.8565

Max Act: 1.7593. Min Act: -0.1700

Data Index: 1270534 (Open Web Text)

Max Activating Token Index: 263