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

Dataset: Open Web Text

Neuron 378 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: 5.2145. Min Range: -5.2145

Max Act: 5.2145. Min Act: -0.1700

Data Index: 5774401 (Open Web Text)

Max Activating Token Index: 707

Text #1

Max Range: 5.2145. Min Range: -5.2145

Max Act: 5.1644. Min Act: -0.1700

Data Index: 2339148 (Open Web Text)

Max Activating Token Index: 622

Text #2

Max Range: 5.2145. Min Range: -5.2145

Max Act: 5.1090. Min Act: -0.1700

Data Index: 2538422 (Open Web Text)

Max Activating Token Index: 424

Text #3

Max Range: 5.2145. Min Range: -5.2145

Max Act: 5.0261. Min Act: -0.1700

Data Index: 7305787 (Open Web Text)

Max Activating Token Index: 603

Text #4

Max Range: 5.2145. Min Range: -5.2145

Max Act: 5.0092. Min Act: -0.1700

Data Index: 1153960 (Open Web Text)

Max Activating Token Index: 138

Text #5

Max Range: 5.2145. Min Range: -5.2145

Max Act: 4.9741. Min Act: -0.1700

Data Index: 6703671 (Open Web Text)

Max Activating Token Index: 174

Text #6

Max Range: 5.2145. Min Range: -5.2145

Max Act: 4.9801. Min Act: -0.1700

Data Index: 7276092 (Open Web Text)

Max Activating Token Index: 79

Text #7

Max Range: 5.2145. Min Range: -5.2145

Max Act: 5.0005. Min Act: -0.1700

Data Index: 4575259 (Open Web Text)

Max Activating Token Index: 361

Text #8

Max Range: 5.2145. Min Range: -5.2145

Max Act: 4.9305. Min Act: -0.1700

Data Index: 2308884 (Open Web Text)

Max Activating Token Index: 72

Text #9

Max Range: 5.2145. Min Range: -5.2145

Max Act: 4.9330. Min Act: -0.1700

Data Index: 7665361 (Open Web Text)

Max Activating Token Index: 37

Text #10

Max Range: 5.2145. Min Range: -5.2145

Max Act: 4.9427. Min Act: -0.1700

Data Index: 3918589 (Open Web Text)

Max Activating Token Index: 490

Text #11

Max Range: 5.2145. Min Range: -5.2145

Max Act: 4.9092. Min Act: -0.1700

Data Index: 6181249 (Open Web Text)

Max Activating Token Index: 617

Text #12

Max Range: 5.2145. Min Range: -5.2145

Max Act: 4.8981. Min Act: -0.1700

Data Index: 6037142 (Open Web Text)

Max Activating Token Index: 717

Text #13

Max Range: 5.2145. Min Range: -5.2145

Max Act: 4.9031. Min Act: -0.1700

Data Index: 8408546 (Open Web Text)

Max Activating Token Index: 533

Text #14

Max Range: 5.2145. Min Range: -5.2145

Max Act: 4.8732. Min Act: -0.1700

Data Index: 5318721 (Open Web Text)

Max Activating Token Index: 356

Text #15

Max Range: 5.2145. Min Range: -5.2145

Max Act: 4.9013. Min Act: -0.1698

Data Index: 3566349 (Open Web Text)

Max Activating Token Index: 97

Text #16

Max Range: 5.2145. Min Range: -5.2145

Max Act: 4.8371. Min Act: -0.1700

Data Index: 79773 (Open Web Text)

Max Activating Token Index: 473

Text #17

Max Range: 5.2145. Min Range: -5.2145

Max Act: 4.8153. Min Act: -0.1700

Data Index: 6825317 (Open Web Text)

Max Activating Token Index: 644

Text #18

Max Range: 5.2145. Min Range: -5.2145

Max Act: 4.7917. Min Act: -0.1700

Data Index: 7266070 (Open Web Text)

Max Activating Token Index: 70

Text #19

Max Range: 5.2145. Min Range: -5.2145

Max Act: 4.8264. Min Act: -0.1700

Data Index: 7647964 (Open Web Text)

Max Activating Token Index: 65