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

Dataset: Open Web Text

Neuron 3035 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: 1.0535. Min Range: -1.0535

Max Act: 1.0483. Min Act: -0.1700

Data Index: 8330338 (Open Web Text)

Max Activating Token Index: 26

Text #1

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0507. Min Act: -0.1700

Data Index: 4863998 (Open Web Text)

Max Activating Token Index: 24

Text #2

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0535. Min Act: -0.1700

Data Index: 6997680 (Open Web Text)

Max Activating Token Index: 23

Text #3

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0307. Min Act: -0.1700

Data Index: 1614060 (Open Web Text)

Max Activating Token Index: 23

Text #4

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0211. Min Act: -0.1700

Data Index: 2014618 (Open Web Text)

Max Activating Token Index: 21

Text #5

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0127. Min Act: -0.1700

Data Index: 7750030 (Open Web Text)

Max Activating Token Index: 26

Text #6

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0172. Min Act: -0.1700

Data Index: 5874735 (Open Web Text)

Max Activating Token Index: 22

Text #7

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0156. Min Act: -0.1700

Data Index: 9321 (Open Web Text)

Max Activating Token Index: 24

Text #8

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0165. Min Act: -0.1700

Data Index: 1262656 (Open Web Text)

Max Activating Token Index: 24

Text #9

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0000. Min Act: -0.1700

Data Index: 7316539 (Open Web Text)

Max Activating Token Index: 26

Text #10

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0047. Min Act: -0.1700

Data Index: 738074 (Open Web Text)

Max Activating Token Index: 25

Text #11

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0029. Min Act: -0.1700

Data Index: 4359261 (Open Web Text)

Max Activating Token Index: 23

Text #12

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0083. Min Act: -0.1700

Data Index: 713802 (Open Web Text)

Max Activating Token Index: 23

Text #13

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0038. Min Act: -0.1700

Data Index: 3885270 (Open Web Text)

Max Activating Token Index: 26

Text #14

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0069. Min Act: -0.1700

Data Index: 6349262 (Open Web Text)

Max Activating Token Index: 24

Text #15

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0098. Min Act: -0.1700

Data Index: 6026661 (Open Web Text)

Max Activating Token Index: 24

Text #16

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0061. Min Act: -0.1700

Data Index: 3533159 (Open Web Text)

Max Activating Token Index: 21

Text #17

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0098. Min Act: -0.1700

Data Index: 5904695 (Open Web Text)

Max Activating Token Index: 25

Text #18

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0058. Min Act: -0.1700

Data Index: 5199184 (Open Web Text)

Max Activating Token Index: 23

Text #19

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0068. Min Act: -0.1700

Data Index: 979389 (Open Web Text)

Max Activating Token Index: 24