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

Dataset: Open Web Text

Neuron 2907 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: 3.4982. Min Range: -3.4982

Max Act: 3.4982. Min Act: -0.1700

Data Index: 8178312 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.3534. Min Act: -0.1700

Data Index: 7723882 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.3612. Min Act: -0.1700

Data Index: 8204646 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.3597. Min Act: -0.1700

Data Index: 7677811 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.3261. Min Act: -0.1700

Data Index: 5178960 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.3139. Min Act: -0.1700

Data Index: 4528108 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.3120. Min Act: -0.1700

Data Index: 386927 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.3076. Min Act: -0.1700

Data Index: 7563385 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2878. Min Act: -0.1700

Data Index: 6694221 (Open Web Text)

Max Activating Token Index: 678

Text #9

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2923. Min Act: -0.1700

Data Index: 1577722 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2998. Min Act: -0.1700

Data Index: 4801680 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.3026. Min Act: -0.1700

Data Index: 976659 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2930. Min Act: -0.1700

Data Index: 5632203 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.3001. Min Act: -0.1700

Data Index: 2671545 (Open Web Text)

Max Activating Token Index: 22

Text #14

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2919. Min Act: -0.1700

Data Index: 2391352 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2736. Min Act: -0.1700

Data Index: 8731490 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2742. Min Act: -0.1700

Data Index: 5297730 (Open Web Text)

Max Activating Token Index: 299

Text #17

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2779. Min Act: -0.1700

Data Index: 3534569 (Open Web Text)

Max Activating Token Index: 20

Text #18

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2597. Min Act: -0.1700

Data Index: 4204616 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2426. Min Act: -0.1700

Data Index: 4282842 (Open Web Text)

Max Activating Token Index: 1001