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

Dataset: Open Web Text

Neuron 425 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: 1.5049. Min Range: -1.5049

Max Act: 1.5049. Min Act: -0.1700

Data Index: 3143609 (Open Web Text)

Max Activating Token Index: 32

Text #1

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4198. Min Act: -0.1696

Data Index: 1139006 (Open Web Text)

Max Activating Token Index: 208

Text #2

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4182. Min Act: -0.1700

Data Index: 5191082 (Open Web Text)

Max Activating Token Index: 33

Text #3

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4251. Min Act: -0.1700

Data Index: 6390238 (Open Web Text)

Max Activating Token Index: 647

Text #4

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4054. Min Act: -0.1700

Data Index: 152584 (Open Web Text)

Max Activating Token Index: 54

Text #5

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3963. Min Act: -0.1700

Data Index: 7298214 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3981. Min Act: -0.1700

Data Index: 4828105 (Open Web Text)

Max Activating Token Index: 17

Text #7

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3802. Min Act: -0.1700

Data Index: 6915020 (Open Web Text)

Max Activating Token Index: 94

Text #8

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3750. Min Act: -0.1700

Data Index: 7669456 (Open Web Text)

Max Activating Token Index: 244

Text #9

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3885. Min Act: -0.1700

Data Index: 3893179 (Open Web Text)

Max Activating Token Index: 107

Text #10

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3718. Min Act: -0.1699

Data Index: 3371125 (Open Web Text)

Max Activating Token Index: 681

Text #11

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3716. Min Act: -0.1700

Data Index: 674927 (Open Web Text)

Max Activating Token Index: 41

Text #12

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3718. Min Act: -0.1700

Data Index: 1697495 (Open Web Text)

Max Activating Token Index: 148

Text #13

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3621. Min Act: -0.1696

Data Index: 6555195 (Open Web Text)

Max Activating Token Index: 430

Text #14

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3667. Min Act: -0.1700

Data Index: 8266192 (Open Web Text)

Max Activating Token Index: 713

Text #15

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3671. Min Act: -0.1700

Data Index: 992052 (Open Web Text)

Max Activating Token Index: 941

Text #16

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3666. Min Act: -0.1700

Data Index: 2396432 (Open Web Text)

Max Activating Token Index: 763

Text #17

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3691. Min Act: -0.1700

Data Index: 5720361 (Open Web Text)

Max Activating Token Index: 103

Text #18

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3685. Min Act: -0.1700

Data Index: 5259509 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3570. Min Act: -0.1700

Data Index: 2627398 (Open Web Text)

Max Activating Token Index: 237