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

Dataset: Open Web Text

Neuron 1208 in Layer 4

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: 3.1045. Min Range: -3.1045

Max Act: 3.1045. Min Act: -0.1700

Data Index: 7600645 (Open Web Text)

Max Activating Token Index: 471

Text #1

Max Range: 3.1045. Min Range: -3.1045

Max Act: 3.0473. Min Act: -0.1700

Data Index: 3773012 (Open Web Text)

Max Activating Token Index: 385

Text #2

Max Range: 3.1045. Min Range: -3.1045

Max Act: 2.9764. Min Act: -0.1700

Data Index: 6604147 (Open Web Text)

Max Activating Token Index: 656

Text #3

Max Range: 3.1045. Min Range: -3.1045

Max Act: 2.9413. Min Act: -0.1700

Data Index: 1695068 (Open Web Text)

Max Activating Token Index: 433

Text #4

Max Range: 3.1045. Min Range: -3.1045

Max Act: 2.9232. Min Act: -0.1700

Data Index: 6796442 (Open Web Text)

Max Activating Token Index: 41

Text #5

Max Range: 3.1045. Min Range: -3.1045

Max Act: 2.9232. Min Act: -0.1700

Data Index: 8690000 (Open Web Text)

Max Activating Token Index: 41

Text #6

Max Range: 3.1045. Min Range: -3.1045

Max Act: 2.9215. Min Act: -0.1700

Data Index: 2794849 (Open Web Text)

Max Activating Token Index: 47

Text #7

Max Range: 3.1045. Min Range: -3.1045

Max Act: 2.9215. Min Act: -0.1700

Data Index: 5248672 (Open Web Text)

Max Activating Token Index: 47

Text #8

Max Range: 3.1045. Min Range: -3.1045

Max Act: 2.8992. Min Act: -0.1700

Data Index: 6854369 (Open Web Text)

Max Activating Token Index: 114

Text #9

Max Range: 3.1045. Min Range: -3.1045

Max Act: 2.9182. Min Act: -0.1700

Data Index: 7910257 (Open Web Text)

Max Activating Token Index: 50

Text #10

Max Range: 3.1045. Min Range: -3.1045

Max Act: 2.8992. Min Act: -0.1700

Data Index: 5371566 (Open Web Text)

Max Activating Token Index: 114

Text #11

Max Range: 3.1045. Min Range: -3.1045

Max Act: 2.8992. Min Act: -0.1700

Data Index: 4029643 (Open Web Text)

Max Activating Token Index: 114

Text #12

Max Range: 3.1045. Min Range: -3.1045

Max Act: 2.9037. Min Act: -0.1700

Data Index: 6453424 (Open Web Text)

Max Activating Token Index: 46

Text #13

Max Range: 3.1045. Min Range: -3.1045

Max Act: 2.9079. Min Act: -0.1700

Data Index: 1023642 (Open Web Text)

Max Activating Token Index: 113

Text #14

Max Range: 3.1045. Min Range: -3.1045

Max Act: 2.9015. Min Act: -0.1700

Data Index: 2768800 (Open Web Text)

Max Activating Token Index: 105

Text #15

Max Range: 3.1045. Min Range: -3.1045

Max Act: 2.8950. Min Act: -0.1700

Data Index: 4297374 (Open Web Text)

Max Activating Token Index: 107

Text #16

Max Range: 3.1045. Min Range: -3.1045

Max Act: 2.8950. Min Act: -0.1700

Data Index: 4029645 (Open Web Text)

Max Activating Token Index: 107

Text #17

Max Range: 3.1045. Min Range: -3.1045

Max Act: 2.9015. Min Act: -0.1700

Data Index: 6452806 (Open Web Text)

Max Activating Token Index: 105

Text #18

Max Range: 3.1045. Min Range: -3.1045

Max Act: 2.8950. Min Act: -0.1700

Data Index: 5371568 (Open Web Text)

Max Activating Token Index: 107

Text #19

Max Range: 3.1045. Min Range: -3.1045

Max Act: 2.8974. Min Act: -0.1700

Data Index: 5300215 (Open Web Text)

Max Activating Token Index: 43