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

Dataset: Open Web Text

Neuron 2736 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: 2.0157. Min Range: -2.0157

Max Act: 2.0157. Min Act: -0.1700

Data Index: 473158 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.9722. Min Act: -0.1700

Data Index: 6179575 (Open Web Text)

Max Activating Token Index: 128

Text #2

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.9731. Min Act: -0.1700

Data Index: 8669852 (Open Web Text)

Max Activating Token Index: 78

Text #3

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.9723. Min Act: -0.1700

Data Index: 828484 (Open Web Text)

Max Activating Token Index: 20

Text #4

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.9557. Min Act: -0.1700

Data Index: 1514414 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.9449. Min Act: -0.1700

Data Index: 4883210 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.9261. Min Act: -0.1700

Data Index: 5420766 (Open Web Text)

Max Activating Token Index: 99

Text #7

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.9251. Min Act: -0.1700

Data Index: 729006 (Open Web Text)

Max Activating Token Index: 794

Text #8

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.9453. Min Act: -0.1700

Data Index: 6459458 (Open Web Text)

Max Activating Token Index: 32

Text #9

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.9386. Min Act: -0.1700

Data Index: 8216506 (Open Web Text)

Max Activating Token Index: 820

Text #10

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.9120. Min Act: -0.1700

Data Index: 320971 (Open Web Text)

Max Activating Token Index: 71

Text #11

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.9067. Min Act: -0.1700

Data Index: 7450919 (Open Web Text)

Max Activating Token Index: 674

Text #12

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.9183. Min Act: -0.1700

Data Index: 7689068 (Open Web Text)

Max Activating Token Index: 733

Text #13

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.9117. Min Act: -0.1700

Data Index: 3269030 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.9217. Min Act: -0.1700

Data Index: 6945296 (Open Web Text)

Max Activating Token Index: 402

Text #15

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.9234. Min Act: -0.1700

Data Index: 1944659 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.9009. Min Act: -0.1700

Data Index: 7879710 (Open Web Text)

Max Activating Token Index: 29

Text #17

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.8934. Min Act: -0.1700

Data Index: 1503419 (Open Web Text)

Max Activating Token Index: 180

Text #18

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.9009. Min Act: -0.1700

Data Index: 6312944 (Open Web Text)

Max Activating Token Index: 49

Text #19

Max Range: 2.0157. Min Range: -2.0157

Max Act: 1.8971. Min Act: -0.1700

Data Index: 1682059 (Open Web Text)

Max Activating Token Index: 6