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

Dataset: Open Web Text

Neuron 2924 in Layer 0

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: 3.2799. Min Range: -3.2799

Max Act: 3.2799. Min Act: -0.1700

Data Index: 313947 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.2799. Min Range: -3.2799

Max Act: 3.2588. Min Act: -0.1700

Data Index: 871889 (Open Web Text)

Max Activating Token Index: 649

Text #2

Max Range: 3.2799. Min Range: -3.2799

Max Act: 3.2550. Min Act: -0.1700

Data Index: 7860386 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.2799. Min Range: -3.2799

Max Act: 3.2397. Min Act: -0.1700

Data Index: 2094401 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.2799. Min Range: -3.2799

Max Act: 3.2303. Min Act: -0.1700

Data Index: 7164224 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.2799. Min Range: -3.2799

Max Act: 3.2224. Min Act: -0.1700

Data Index: 2950390 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.2799. Min Range: -3.2799

Max Act: 3.2301. Min Act: -0.1700

Data Index: 2776229 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.2799. Min Range: -3.2799

Max Act: 3.2272. Min Act: -0.1700

Data Index: 4323072 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.2799. Min Range: -3.2799

Max Act: 3.2069. Min Act: -0.1700

Data Index: 3405307 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 3.2799. Min Range: -3.2799

Max Act: 3.2091. Min Act: -0.1700

Data Index: 6265774 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.2799. Min Range: -3.2799

Max Act: 3.1930. Min Act: -0.1700

Data Index: 4175195 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.2799. Min Range: -3.2799

Max Act: 3.1964. Min Act: -0.1700

Data Index: 4991521 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.2799. Min Range: -3.2799

Max Act: 3.1787. Min Act: -0.1700

Data Index: 2174391 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 3.2799. Min Range: -3.2799

Max Act: 3.1797. Min Act: -0.1700

Data Index: 2219689 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 3.2799. Min Range: -3.2799

Max Act: 3.1712. Min Act: -0.1700

Data Index: 178535 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.2799. Min Range: -3.2799

Max Act: 3.1875. Min Act: -0.1700

Data Index: 151418 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 3.2799. Min Range: -3.2799

Max Act: 3.1810. Min Act: -0.1700

Data Index: 4326555 (Open Web Text)

Max Activating Token Index: 563

Text #17

Max Range: 3.2799. Min Range: -3.2799

Max Act: 3.1755. Min Act: -0.1700

Data Index: 1255456 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.2799. Min Range: -3.2799

Max Act: 3.1720. Min Act: -0.1700

Data Index: 5474481 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 3.2799. Min Range: -3.2799

Max Act: 3.1728. Min Act: -0.1700

Data Index: 338119 (Open Web Text)

Max Activating Token Index: 3