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

Dataset: Open Web Text

Neuron 2670 in Layer 2

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: 0.9058. Min Range: -0.9058

Max Act: 0.9058. Min Act: -0.1700

Data Index: 1879026 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.7582. Min Act: -0.1700

Data Index: 2970039 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.6052. Min Act: -0.1699

Data Index: 6631215 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.6083. Min Act: -0.1700

Data Index: 3307792 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.5773. Min Act: -0.1700

Data Index: 3546530 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.5569. Min Act: -0.1700

Data Index: 125047 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.5692. Min Act: -0.1700

Data Index: 1158479 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.5659. Min Act: -0.1698

Data Index: 348614 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.5670. Min Act: -0.1697

Data Index: 5556750 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.5743. Min Act: -0.1700

Data Index: 6539086 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.5534. Min Act: -0.1700

Data Index: 3790831 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.5466. Min Act: -0.1700

Data Index: 1055908 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.5522. Min Act: -0.1700

Data Index: 5607816 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.5532. Min Act: -0.1696

Data Index: 3764769 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.5432. Min Act: -0.1700

Data Index: 2691187 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.5435. Min Act: -0.1700

Data Index: 6634054 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.5228. Min Act: -0.1700

Data Index: 5082991 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.5390. Min Act: -0.1700

Data Index: 2232517 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.5293. Min Act: -0.1697

Data Index: 5230720 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 0.9058. Min Range: -0.9058

Max Act: 0.5382. Min Act: -0.1700

Data Index: 4284378 (Open Web Text)

Max Activating Token Index: 3