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

Dataset: Open Web Text

Neuron 174 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: 1.9231. Min Range: -1.9231

Max Act: 1.9231. Min Act: -0.1700

Data Index: 1953833 (Open Web Text)

Max Activating Token Index: 23

Text #1

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.9021. Min Act: -0.1700

Data Index: 5885898 (Open Web Text)

Max Activating Token Index: 119

Text #2

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8679. Min Act: -0.1700

Data Index: 1992583 (Open Web Text)

Max Activating Token Index: 160

Text #3

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8608. Min Act: -0.1700

Data Index: 5281818 (Open Web Text)

Max Activating Token Index: 58

Text #4

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8553. Min Act: -0.1700

Data Index: 4468127 (Open Web Text)

Max Activating Token Index: 34

Text #5

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8337. Min Act: -0.1700

Data Index: 6091095 (Open Web Text)

Max Activating Token Index: 56

Text #6

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8214. Min Act: -0.1700

Data Index: 7810442 (Open Web Text)

Max Activating Token Index: 18

Text #7

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8146. Min Act: -0.1700

Data Index: 360846 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8057. Min Act: -0.1700

Data Index: 203341 (Open Web Text)

Max Activating Token Index: 36

Text #9

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.7954. Min Act: -0.1700

Data Index: 7934291 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.8006. Min Act: -0.1700

Data Index: 4578839 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.7923. Min Act: -0.1700

Data Index: 1575591 (Open Web Text)

Max Activating Token Index: 393

Text #12

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.7811. Min Act: -0.1700

Data Index: 1209716 (Open Web Text)

Max Activating Token Index: 135

Text #13

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.7756. Min Act: -0.1700

Data Index: 3458984 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.7725. Min Act: -0.1700

Data Index: 3716387 (Open Web Text)

Max Activating Token Index: 206

Text #15

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.7834. Min Act: -0.1700

Data Index: 8414561 (Open Web Text)

Max Activating Token Index: 268

Text #16

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.7724. Min Act: -0.1700

Data Index: 1678305 (Open Web Text)

Max Activating Token Index: 155

Text #17

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.7680. Min Act: -0.1700

Data Index: 6157296 (Open Web Text)

Max Activating Token Index: 43

Text #18

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.7647. Min Act: -0.1700

Data Index: 4705845 (Open Web Text)

Max Activating Token Index: 50

Text #19

Max Range: 1.9231. Min Range: -1.9231

Max Act: 1.7645. Min Act: -0.1700

Data Index: 5732346 (Open Web Text)

Max Activating Token Index: 295