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

Dataset: Open Web Text

Neuron 1011 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: 3.1520. Min Range: -3.1520

Max Act: 3.1520. Min Act: -0.1700

Data Index: 1700405 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 3.1520. Min Range: -3.1520

Max Act: 3.0412. Min Act: -0.1700

Data Index: 7479720 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 3.1520. Min Range: -3.1520

Max Act: 3.0031. Min Act: -0.1700

Data Index: 1997098 (Open Web Text)

Max Activating Token Index: 22

Text #3

Max Range: 3.1520. Min Range: -3.1520

Max Act: 2.9596. Min Act: -0.1700

Data Index: 5446819 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.1520. Min Range: -3.1520

Max Act: 2.9586. Min Act: -0.1700

Data Index: 7787317 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.1520. Min Range: -3.1520

Max Act: 2.9337. Min Act: -0.1700

Data Index: 2595493 (Open Web Text)

Max Activating Token Index: 43

Text #6

Max Range: 3.1520. Min Range: -3.1520

Max Act: 2.9405. Min Act: -0.1700

Data Index: 2981504 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.1520. Min Range: -3.1520

Max Act: 2.9406. Min Act: -0.1700

Data Index: 1971836 (Open Web Text)

Max Activating Token Index: 19

Text #8

Max Range: 3.1520. Min Range: -3.1520

Max Act: 2.9327. Min Act: -0.1700

Data Index: 2538710 (Open Web Text)

Max Activating Token Index: 919

Text #9

Max Range: 3.1520. Min Range: -3.1520

Max Act: 2.9274. Min Act: -0.1700

Data Index: 7662370 (Open Web Text)

Max Activating Token Index: 57

Text #10

Max Range: 3.1520. Min Range: -3.1520

Max Act: 2.9166. Min Act: -0.1700

Data Index: 3499162 (Open Web Text)

Max Activating Token Index: 39

Text #11

Max Range: 3.1520. Min Range: -3.1520

Max Act: 2.9138. Min Act: -0.1700

Data Index: 2977703 (Open Web Text)

Max Activating Token Index: 30

Text #12

Max Range: 3.1520. Min Range: -3.1520

Max Act: 2.9251. Min Act: -0.1700

Data Index: 1208570 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.1520. Min Range: -3.1520

Max Act: 2.9314. Min Act: -0.1700

Data Index: 2062085 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.1520. Min Range: -3.1520

Max Act: 2.9232. Min Act: -0.1700

Data Index: 4363178 (Open Web Text)

Max Activating Token Index: 34

Text #15

Max Range: 3.1520. Min Range: -3.1520

Max Act: 2.8882. Min Act: -0.1700

Data Index: 2849996 (Open Web Text)

Max Activating Token Index: 512

Text #16

Max Range: 3.1520. Min Range: -3.1520

Max Act: 2.9065. Min Act: -0.1700

Data Index: 5102371 (Open Web Text)

Max Activating Token Index: 795

Text #17

Max Range: 3.1520. Min Range: -3.1520

Max Act: 2.9034. Min Act: -0.1700

Data Index: 8286322 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 3.1520. Min Range: -3.1520

Max Act: 2.9063. Min Act: -0.1700

Data Index: 92300 (Open Web Text)

Max Activating Token Index: 463

Text #19

Max Range: 3.1520. Min Range: -3.1520

Max Act: 2.8933. Min Act: -0.1700

Data Index: 3952705 (Open Web Text)

Max Activating Token Index: 993