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

Dataset: Open Web Text

Neuron 132 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: 4.8521. Min Range: -4.8521

Max Act: 4.8521. Min Act: -0.1700

Data Index: 2621235 (Open Web Text)

Max Activating Token Index: 214

Text #1

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.8453. Min Act: -0.1700

Data Index: 7459820 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.8223. Min Act: -0.1700

Data Index: 1212954 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.8003. Min Act: -0.1700

Data Index: 2956038 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7971. Min Act: -0.1700

Data Index: 4903385 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7717. Min Act: -0.1700

Data Index: 8018156 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7878. Min Act: -0.1700

Data Index: 7328780 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7673. Min Act: -0.1700

Data Index: 2020444 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7939. Min Act: -0.1700

Data Index: 6596028 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7858. Min Act: -0.1700

Data Index: 6380398 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7936. Min Act: -0.1700

Data Index: 5681402 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7656. Min Act: -0.1700

Data Index: 4691591 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7747. Min Act: -0.1700

Data Index: 1571823 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7877. Min Act: -0.1700

Data Index: 4406311 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7725. Min Act: -0.1700

Data Index: 3656083 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7818. Min Act: -0.1700

Data Index: 1269633 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7735. Min Act: -0.1700

Data Index: 3164697 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7773. Min Act: -0.1700

Data Index: 565688 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7816. Min Act: -0.1700

Data Index: 943628 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7576. Min Act: -0.1700

Data Index: 2475274 (Open Web Text)

Max Activating Token Index: 5