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

Dataset: Open Web Text

Neuron 3034 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: 4.9585. Min Range: -4.9585

Max Act: 4.9585. Min Act: -0.1700

Data Index: 4477541 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.9585. Min Range: -4.9585

Max Act: 4.9530. Min Act: -0.1700

Data Index: 248310 (Open Web Text)

Max Activating Token Index: 52

Text #2

Max Range: 4.9585. Min Range: -4.9585

Max Act: 4.9210. Min Act: -0.1700

Data Index: 6966271 (Open Web Text)

Max Activating Token Index: 26

Text #3

Max Range: 4.9585. Min Range: -4.9585

Max Act: 4.9029. Min Act: -0.1700

Data Index: 4264786 (Open Web Text)

Max Activating Token Index: 30

Text #4

Max Range: 4.9585. Min Range: -4.9585

Max Act: 4.8994. Min Act: -0.1694

Data Index: 65771 (Open Web Text)

Max Activating Token Index: 70

Text #5

Max Range: 4.9585. Min Range: -4.9585

Max Act: 4.8707. Min Act: -0.1700

Data Index: 2428528 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 4.9585. Min Range: -4.9585

Max Act: 4.8546. Min Act: -0.1700

Data Index: 2802155 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.9585. Min Range: -4.9585

Max Act: 4.8685. Min Act: -0.1700

Data Index: 7752535 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.9585. Min Range: -4.9585

Max Act: 4.8703. Min Act: -0.1700

Data Index: 5386465 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.9585. Min Range: -4.9585

Max Act: 4.8819. Min Act: -0.1700

Data Index: 5192893 (Open Web Text)

Max Activating Token Index: 64

Text #10

Max Range: 4.9585. Min Range: -4.9585

Max Act: 4.8941. Min Act: -0.1700

Data Index: 4838188 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.9585. Min Range: -4.9585

Max Act: 4.8856. Min Act: -0.1700

Data Index: 7810995 (Open Web Text)

Max Activating Token Index: 47

Text #12

Max Range: 4.9585. Min Range: -4.9585

Max Act: 4.8454. Min Act: -0.1699

Data Index: 3401310 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 4.9585. Min Range: -4.9585

Max Act: 4.8573. Min Act: -0.1700

Data Index: 5200661 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.9585. Min Range: -4.9585

Max Act: 4.8733. Min Act: -0.1700

Data Index: 5772920 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.9585. Min Range: -4.9585

Max Act: 4.8692. Min Act: -0.1700

Data Index: 4080674 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.9585. Min Range: -4.9585

Max Act: 4.8334. Min Act: -0.1700

Data Index: 6661702 (Open Web Text)

Max Activating Token Index: 75

Text #17

Max Range: 4.9585. Min Range: -4.9585

Max Act: 4.8346. Min Act: -0.1700

Data Index: 3367280 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.9585. Min Range: -4.9585

Max Act: 4.8576. Min Act: -0.1700

Data Index: 6912935 (Open Web Text)

Max Activating Token Index: 513

Text #19

Max Range: 4.9585. Min Range: -4.9585

Max Act: 4.8345. Min Act: -0.1700

Data Index: 2859688 (Open Web Text)

Max Activating Token Index: 11